| Title: | 115 Data Sets from "Introductory Econometrics: A Modern Approach, 7e" by Jeffrey M. Wooldridge |
|---|---|
| Description: | Students learning both econometrics and R may find the introduction to both challenging. The wooldridge data package aims to lighten the task by efficiently loading any data set found in the text with a single command. Data sets have been compressed to a fraction of their original size. Documentation files contain page numbers, the original source, time of publication, and notes from the author suggesting avenues for further analysis and research. If one needs an introduction to R model syntax, a vignette contains solutions to examples from chapters of the text. Data sets are from the 7th edition (Wooldridge 2020, ISBN-13 978-1-337-55886-0), and are backwards compatible with all previous versions of the text. |
| Authors: | Justin M. Shea [aut, cre], Kennth H. Brown [ctb] |
| Maintainer: | Justin M. Shea <[email protected]> |
| License: | GPL-3 |
| Version: | 1.4-3 |
| Built: | 2024-10-31 21:09:09 UTC |
| Source: | https://github.com/justinmshea/wooldridge |
Wooldridge Source: Data from the National Highway Traffic Safety Administration: “A Digest of State Alcohol-Highway Safety Related Legislation,” U.S. Department of Transportation, NHTSA. I used the third (1985), eighth (1990), and 13th (1995) editions. Data loads lazily.
data('admnrev')data('admnrev')
A data.frame with 153 observations on 5 variables:
state: state postal code
year: 85, 90, or 95
admnrev: =1 if admin. revoc. law
daysfrst: days suspended, first offense
daysscnd: days suspended, second offense
This is not so much a data set as a summary of so-called “administrative per se” laws atthe state level, for three different years. It could be supplemented with drunk-driving fatalities for a nice econometric analysis. In addition, the data for 2000 or later years can be added, forming the basis for a term project. Many other explanatory variables could be included. Unemployment rates, state-level tax rates on alcohol, and membership in MADD are just a few possibilities.
Used in Text: not used
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(admnrev)str(admnrev)
Wooldridge Source: R.C. Fair (1978), “A Theory of Extramarital Affairs,” Journal of Political Economy 86, 45-61, 1978. I collected the data from Professor Fair’s web cite at the Yale University Department of Economics. He originally obtained the data from a survey by Psychology Today. Data loads lazily.
data('affairs')data('affairs')
A data.frame with 601 observations on 19 variables:
id: identifier
male: =1 if male
age: in years
yrsmarr: years married
kids: =1 if have kids
relig: 5 = very relig., 4 = somewhat, 3 = slightly, 2 = not at all, 1 = anti
educ: years schooling
occup: occupation, reverse Hollingshead scale
ratemarr: 5 = vry hap marr, 4 = hap than avg, 3 = avg, 2 = smewht unhap, 1 = vry unhap
naffairs: number of affairs within last year
affair: =1 if had at least one affair
vryhap: ratemarr == 5
hapavg: ratemarr == 4
avgmarr: ratemarr == 3
unhap: ratemarr == 2
vryrel: relig == 5
smerel: relig == 4
slghtrel: relig == 3
notrel: relig == 2
This is an interesting data set for problem sets starting in Chapter 7. Even though naffairs (number of extramarital affairs a woman reports) is a count variable, a linear model can be used to model its conditional mean as an approximation. Or, you could ask the students to estimate a linear probability model for the binary indicator affair, equal to one of the woman reports having any extramarital affairs. One possibility is to test whether putting the single marriage rating variable, ratemarr, is enough, against the alternative that a full set of dummy variables is needed; see pages 239-240 for a similar example. This is also a good data set to illustrate Poisson regression (using naffairs) in Section 17.3 or probit and logit (using affair) in Section 17.1.
Used in Text: not used
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(affairs)str(affairs)
Wooldridge Source: Jiyoung Kwon, a former doctoral student in economics at MSU, kindly provided these data, which she obtained from the Domestic Airline Fares Consumer Report by the U.S. Department of Transportation. Data loads lazily.
data('airfare')data('airfare')
A data.frame with 4596 observations on 14 variables:
year: 1997, 1998, 1999, 2000
id: route identifier
dist: distance, in miles
passen: avg. passengers per day
fare: avg. one-way fare, $
bmktshr: fraction market, biggest carrier
ldist: log(distance)
y98: =1 if year == 1998
y99: =1 if year == 1999
y00: =1 if year == 2000
lfare: log(fare)
ldistsq: ldist^2
concen: = bmktshr
lpassen: log(passen)
This data set nicely illustrates the different estimates obtained when applying pooled OLS, random effects, and fixed effects.
Used in Text: pages 506-507, 581
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(airfare)str(airfare)
Wooldridge Source: Terza, J.V. (2002), “Alcohol Abuse and Employment: A Second Look,” Journal of Applied Econometrics 17, 393-404. I obtained these data from the Journal of Applied Econometrics data archive at http://qed.econ.queensu.ca/jae/. Data loads lazily.
data('alcohol')data('alcohol')
A data.frame with 9822 observations on 33 variables:
abuse: =1 if abuse alcohol
status: out of workforce = 1; unemployed = 2, employed = 3
unemrate: state unemployment rate
age: age in years
educ: years of schooling
married: =1 if married
famsize: family size
white: =1 if white
exhealth: =1 if in excellent health
vghealth: =1 if in very good health
goodhealth: =1 if in good health
fairhealth: =1 if in fair health
northeast: =1 if live in northeast
midwest: =1 if live in midwest
south: =1 if live in south
centcity: =1 if live in central city of MSA
outercity: =1 if in outer city of MSA
qrt1: =1 if interviewed in first quarter
qrt2: =1 if interviewed in second quarter
qrt3: =1 if interviewed in third quarter
beertax: state excise tax, $ per gallon
cigtax: state cigarette tax, cents per pack
ethanol: state per-capita ethanol consumption
mothalc: =1 if mother an alcoholic
fathalc: =1 if father an alcoholic
livealc: =1 if lived with alcoholic
inwf: =1 if status > 1
employ: =1 if employed
agesq: age^2
beertaxsq: beertax^2
cigtaxsq: cigtax^2
ethanolsq: ethanol^2
educsq: educ^2
page 629
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(alcohol)str(alcohol)
Wooldridge Source: These data were used in the doctoral dissertation of Jeffrey Blend, Department of Agricultural Economics, Michigan State University, 1998. The thesis was supervised by Professor Eileen van Ravensway. Drs. Blend and van Ravensway kindly provided the data, which were obtained from a telephone survey conducted by the Institute for Public Policy and Social Research at MSU. Data loads lazily.
data('apple')data('apple')
A data.frame with 660 observations on 17 variables:
id: respondent identifier
educ: years schooling
date: date: month/day/year
state: home state
regprc: price of regular apples
ecoprc: price of ecolabeled apples
inseason: =1 if interviewed in Nov.
hhsize: household size
male: =1 if male
faminc: family income, thousands
age: in years
reglbs: quantity regular apples, pounds
ecolbs: quantity ecolabeled apples, lbs
numlt5: # in household younger than 5
num5_17: # in household 5 to 17
num18_64: # in household 18 to 64
numgt64: # in household older than 64
This data set is close to a true experimental data set because the price pairs facing a family were randomly determined. In other words, the family head was presented with prices for the eco-labeled and regular apples, and then asked how much of each kind of apple the family would buy at the given prices. As predicted by basic economics, the own price effect is negative (and strong) and the cross price effect is positive (and strong). While the main dependent variable, ecolbs, piles up at zero, estimating a linear model is still worthwhile. Interestingly, because the survey design induces a strong positive correlation between the prices of eco-labeled and regular apples, there is an omitted variable problem if either of the price variables is dropped from the demand equation. A good exam question is to show a simple regression of ecolbs on ecoprc and then a multiple regression on both prices, and ask students to decide whether the price variables must be positively or negatively correlated.
Used in Text: pages 201, 223, 266, 626-627
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(apple)str(apple)
Wooldridge Source: Harbridge, L., J. Krosnick, and J.M. Wooldridge (forthcoming), “Presidential Approval and Gas Prices: Sociotropic or Pocketbook Influence?” in New Explorations in Political Psychology, ed. J. Krosnick. New York: Psychology Press (Taylor and Francis Group). Professor Harbridge kindly provided the data, of which I have used a subset. Data loads lazily.
data('approval')data('approval')
A data.frame with 78 observations on 16 variables:
id: id
month: month
year: year
sp500: S&P 500 index
cpi: Consumer Price Index
cpifood: CPI for food
approve: Gallup approval rate, percent
gasprice: average gas price, cents
unemploy: unemployment rate, percent
katrina: =1 for three months after Hurricane Katrina
rgasprice: real gas price, 100*(gasprice/cpi)
lrgasprice: log(rgasprice)
sep11: =1 for 09/2001 and two months following
iraqinvade: =1 for three months after Iraq invasion
lsp500: log(sp500)
lcpifood: log(cpifood)
343, 371, 400
http://www.cengage.com/c/introductory-econometrics-a-modern-approach-6e-wooldridge
str(approval)str(approval)
Wooldridge Sources: Peterson's Guide to Four Year Colleges, 1994 and 1995 (24th and 25th editions). Princeton University Press. Princeton, NJ. The Official 1995 College Basketball Records Book, 1994, NCAA. 1995 Information Please Sports Almanac (6th edition). Houghton Mifflin. New York, NY. Data loads lazily.
data('athlet1')data('athlet1')
A data.frame with 118 observations on 23 variables:
year: 1992 or 1993
apps: # applics for admission
top25: perc frsh class in 25 hs perc
ver500: perc frsh >= 500 on verbal SAT
mth500: perc frsh >= 500 on math SAT
stufac: student-faculty ratio
bowl: = 1 if bowl game in prev yr
btitle: = 1 if men's cnf chmps prv yr
finfour: = 1 if men's final 4 prv yr
lapps: log(apps)
d93: =1 if year = 1993
avg500: (ver500+mth500)/2
cfinfour: change in finfour
clapps: change in lapps
cstufac: change in stufac
cbowl: change in bowl
cavg500: change in avg500
cbtitle: change in btitle
lapps_1: lapps lagged
school: name of university
ctop25: change in top25
bball: =1 if btitle or finfour
cbball: change in bball
These data were collected by Patrick Tulloch, an MSU economics major, for a term project. The “athletic success” variables are for the year prior to the enrollment and academic data. Updating these data to get a longer stretch of years, and including appearances in the “Sweet 16” NCAA basketball tournaments, would make for a more convincing analysis. With the growing popularity of women’s sports, especially basketball, an analysis that includes success in women’s athletics would be interesting.
Used in Text: page 697
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(athlet1)str(athlet1)
Wooldridge Sources: Peterson's Guide to Four Year Colleges, 1995 (25th edition). Princeton University Press. 1995 Information Please Sports Almanac (6th edition). Houghton Mifflin. New York, NY Data loads lazily.
data('athlet2')data('athlet2')
A data.frame with 30 observations on 10 variables:
dscore: home scr. - vist. scr., 1993
dinstt: diff. in-state tuit., 1994
doutstt: diff. out-state tuit., 1994
htpriv: =1 if home team priv. sch.
vtpriv: =1 if vist. team priv. sch.
dapps: diff. in applications, 1994
htwrd: =1 if home win. record, 1993
vtwrd: =1 if vist. win. record, 1993
dwinrec: htwrd - vtwrd
dpriv: htpriv - vtpriv
These data were collected by Paul Anderson, an MSU economics major, for a term project. The score from football outcomes for natural rivals (Michigan-Michigan State, California-Stanford, Florida-Florida State, to name a few) is matched with application and academic data. The application and tuition data are for Fall 1994. Football records and scores are from 1993 football season. Extended these data to obtain a long stretch of panel data and other “natural” rivals could be very interesting.
Used in Text: page 697
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(athlet2)str(athlet2)
Wooldridge Source: These data were collected by Professors Ronald Fisher and Carl Liedholm during a term in which they both taught principles of microeconomics at Michigan State University. Professors Fisher and Liedholm kindly gave me permission to use a random subset of their data, and their research assistant at the time, Jeffrey Guilfoyle, who completed his Ph.D. in economics at MSU, provided helpful hints. Data loads lazily.
data('attend')data('attend')
A data.frame with 680 observations on 11 variables:
attend: classes attended out of 32
termGPA: GPA for term
priGPA: cumulative GPA prior to term
ACT: ACT score
final: final exam score
atndrte: percent classes attended
hwrte: percent homework turned in
frosh: =1 if freshman
soph: =1 if sophomore
missed: number of classes missed
stndfnl: (final - mean)/sd
The attendance figures were obtained by requiring students to slide their ID cards through a magnetic card reader, under the supervision of a teaching assistant. You might have the students use final, rather than the standardized variable, so that they can see the statistical significance of each variable remains exactly the same. The standardized variable is used only so that the coefficients measure effects in terms of standard deviations from the average score.
Used in Text: pages 111, 152, 199-200, 222
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(attend)str(attend)
Wooldridge Source: These data come from a 1988 Urban Institute audit study in the Washington, D.C. area. I obtained them from the article “The Urban Institute Audit Studies: Their Methods and Findings,” by James J. Heckman and Peter Siegelman. In Fix, M. and Struyk, R., eds., Clear and Convincing Evidence: Measurement of Discrimination in America. Washington, D.C.: Urban Institute Press, 1993, 187-258. Data loads lazily.
data('audit')data('audit')
A data.frame with 241 observations on 3 variables:
w: =1 if white app. got job offer
b: =1 if black app. got job offer
y: b - w
pages 776-777, 784, 787
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(audit)str(audit)
Wooldridge Source: C.M. Krupp and P.S. Pollard (1999), Market Responses to Antidumpting Laws: Some Evidence from the U.S. Chemical Industry, Canadian Journal of Economics 29, 199-227. Dr. Krupp kindly provided the data. They are monthly data covering February 1978 through December 1988. Data loads lazily.
data('barium')data('barium')
A data.frame with 131 observations on 31 variables:
chnimp: Chinese imports, bar. chl.
bchlimp: total imports bar. chl.
befile6: =1 for all 6 mos before filing
affile6: =1 for all 6 mos after filing
afdec6: =1 for all 6 mos after decision
befile12: =1 all 12 mos before filing
affile12: =1 all 12 mos after filing
afdec12: =1 all 12 mos after decision
chempi: chemical production index
gas: gasoline production
rtwex: exchange rate index
spr: =1 for spring months
sum: =1 for summer months
fall: =1 for fall months
lchnimp: log(chnimp)
lgas: log(gas)
lrtwex: log(rtwex)
lchempi: log(chempi)
t: time trend
feb: =1 if month is feb
mar: =1 if month is march
apr:
may:
jun:
jul:
aug:
sep:
oct:
nov:
dec:
percchn: percent imports from china
Rather than just having intercept shifts for the different regimes, one could conduct a full Chow test across the different regimes.
Used in Text: pages 361-362, 372, 377, 426, 442-443, 445, 663, 665, 672
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(barium)str(barium)
Wooldridge Source: Hamermesh, D.S. and J.E. Biddle (1994), “Beauty and the Labor Market,” American Economic Review 84, 1174-1194. Professor Hamermesh kindly provided me with the data. For manageability, I have included only a subset of the variables, which results in somewhat larger sample sizes than reported for the regressions in the Hamermesh and Biddle paper. Data loads lazily.
data('beauty')data('beauty')
A data.frame with 1260 observations on 17 variables:
wage: hourly wage
lwage: log(wage)
belavg: =1 if looks <= 2
abvavg: =1 if looks >=4
exper: years of workforce experience
looks: from 1 to 5
union: =1 if union member
goodhlth: =1 if good health
black: =1 if black
female: =1 if female
married: =1 if married
south: =1 if live in south
bigcity: =1 if live in big city
smllcity: =1 if live in small city
service: =1 if service industry
expersq: exper^2
educ: years of schooling
pages 238-239, 265-266
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(beauty)str(beauty)
Wooldridge Data loads lazily.
data('benefits')data('benefits')
A data.frame with 1848 observations on 18 variables:
distid: district identifier
schid: school identifier
lunch: percent eligible, free lunch
enroll: school enrollment
staff: staff per 1000 students
exppp: expenditures per pupil
avgsal: average teacher salary, $
avgben: average teacher non-salary benefits, $
math4: percent passing 4th grade math test
story4: percent passing 4th grade reading test
bs: avgben/avgsal
lavgsal: log(avgsal)
lenroll: log(enroll)
lstaff: log(staff)
bsbar: within-district avg of bs
lunchbar: within-district avg of lunch
lenrollbar: within-district avg of lenroll
lstaffbar: within-district avg of lstaff
NA
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(benefits)str(benefits)
Wooldridge Data loads lazily.
data('beveridge')data('beveridge')
A data.frame with 135 observations on 8 variables:
month: dec 200 through feb 2012
urate: unemployment rate, percent
vrate: vacancy rate, percent
t: linear time trend
urate_1: L.urate
vrate_1: L.vrate
curate: D.urate
cvrate: D.vrate
NA
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(beveridge)str(beveridge)
Wooldridge Source: O. Baser and E. Pema (2003), “The Return of Publications for Economics Faculty,” Economics Bulletin 1, 1-13. Professors Baser and Pema kindly provided the data. Data loads lazily.
data('big9salary')data('big9salary')
A data.frame with 786 observations on 30 variables:
id: person identifier
year: 92, 95, or 99
salary: annual salary, $
pubindx: publication index
totpge: standardized total article pages
assist: =1 if assistant professor
assoc: =1 if associate professor
prof: =1 if full professor
chair: =1 if department chair
top20phd: =1 if Ph.D. from top 20 dept.
yearphd: year Ph.D. obtained
female: =1 if female
osu: =1 if Ohio State U.
iowa: =1 if U. Iowa
indiana: =1 if Indiana U.
purdue: =1 if Purdue U.
msu: =1 if Michigan State U.
minn: =1 if U. Minnesota
mich: =1 if U. Michigan
wisc: =1 if U. Wisconsin
illinois: =1 if U. Illinois
y92: =1 if year == 92
y95: =1 if year == 95
y99: =1 if year == 99
lsalary: log(salary)
exper: years since first teaching job
expersq: exper^2
pubindxsq: pubindx^2
pubindx0: =1 if pubindx == 0
lpubindx: log(pubindx) if pubindx > 0
This is an unbalanced panel data set in the sense that as many as three years of data are available for each faculty member but where some have fewer than three years. It is not clear that something like a fixed effects or first differencing analysis makes sense: in effect, approaches that remove the heterogeneity control for too much by controlling for unobserved heterogeneity which, in this case, includes faculty intelligence, talent, and motivation. Presumably these factors enter into the publication index. It is hard to think we want to hold the main factors driving productivity fixed when trying to measure the effect of productivity on salary. Pooled OLS regression with “cluster robust” standard errors seems more natural. On the other hand, if we want to measure the return to having a degree from a top 20 Ph.D. program then we would want to control for factors that cause selection into a top 20 program. Unfortunately, this variable does not change over time, and so FD and FE are not applicable.
Used in Text: not used
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(big9salary)str(big9salary)
Wooldridge Source: J. Mullahy (1997), “Instrumental-Variable Estimation of Count Data Models: Applications to Models of Cigarette Smoking Behavior,” Review of Economics and Statistics 79, 596-593. Professor Mullahy kindly provided the data. He obtained them from the 1988 National Health Interview Survey. Data loads lazily.
data('bwght')data('bwght')
A data.frame with 1388 observations on 14 variables:
faminc: 1988 family income, $1000s
cigtax: cig. tax in home state, 1988
cigprice: cig. price in home state, 1988
bwght: birth weight, ounces
fatheduc: father's yrs of educ
motheduc: mother's yrs of educ
parity: birth order of child
male: =1 if male child
white: =1 if white
cigs: cigs smked per day while preg
lbwght: log of bwght
bwghtlbs: birth weight, pounds
packs: packs smked per day while preg
lfaminc: log(faminc)
pages 18, 61, 110, 151, 165, 178, 184, 187-188, 258-259, 522-523
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(bwght)str(bwght)
Wooldridge Source: Dr. Zhehui Luo, a recent MSU Ph.D. in economics and Visiting Research Associate in the Department of Epidemiology at MSU, kindly provided these data. She obtained them from state files linking birth and infant death certificates, and from the National Center for Health Statistics natality and mortality data. Data loads lazily.
data('bwght2')data('bwght2')
A data.frame with 1832 observations on 23 variables:
mage: mother's age, years
meduc: mother's educ, years
monpre: month prenatal care began
npvis: total number of prenatal visits
fage: father's age, years
feduc: father's educ, years
bwght: birth weight, grams
omaps: one minute apgar score
fmaps: five minute apgar score
cigs: avg cigarettes per day
drink: avg drinks per week
lbw: =1 if bwght <= 2000
vlbw: =1 if bwght <= 1500
male: =1 if baby male
mwhte: =1 if mother white
mblck: =1 if mother black
moth: =1 if mother is other
fwhte: =1 if father white
fblck: =1 if father black
foth: =1 if father is other
lbwght: log(bwght)
magesq: mage^2
npvissq: npvis^2
There are many possibilities with this data set. In addition to number of prenatal visits, smoking and alcohol consumption (during pregnancy) are included as explanatory variables. These can be added to equations of the kind found in Exercise C6.10. In addition, the one- and five-minute APGAR scores are included. These are measures of the well being of infants just after birth. An interesting feature of the score is that it is bounded between zero and 10, making a linear model less than ideal. Still, a linear model would be informative, and you might ask students about predicted values less than zero or greater than 10.
Used in Text: pages 184, 223
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(bwght2)str(bwght2)
Wooldridge Source: These data were collected by Daniel Martin, a former MSU undergraduate, for a final project. They come from the FBI Uniform Crime Reports and are for the year 1992. Data loads lazily.
data('campus')data('campus')
A data.frame with 97 observations on 7 variables:
enroll: total enrollment
priv: =1 if private college
police: employed officers
crime: total campus crimes
lcrime: log(crime)
lenroll: log(enroll)
lpolice: log(police)
Colleges and universities are now required to provide much better, more detailed crime data. A very rich data set can now be obtained, even a panel data set for colleges across different years. Statistics on male/female ratios, fraction of men/women in fraternities or sororities, policy variables – such as a “safe house” for women on campus, as was started at MSU in 1994 – could be added as explanatory variables. The crime rate in the host town would be a good control.
Used in Text: pages 131-132
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(campus)str(campus)
Wooldridge Source: D. Card (1995), Using Geographic Variation in College Proximity to Estimate the Return to Schooling, in Aspects of Labour Market Behavior: Essays in Honour of John Vanderkamp. Ed. L.N. Christophides, E.K. Grant, and R. Swidinsky, 201-222. Toronto: University of Toronto Press. Professor Card kindly provided these data. Data loads lazily.
data('card')data('card')
A data.frame with 3010 observations on 34 variables:
id: person identifier
nearc2: =1 if near 2 yr college, 1966
nearc4: =1 if near 4 yr college, 1966
educ: years of schooling, 1976
age: in years
fatheduc: father's schooling
motheduc: mother's schooling
weight: NLS sampling weight, 1976
momdad14: =1 if live with mom, dad at 14
sinmom14: =1 if with single mom at 14
step14: =1 if with step parent at 14
reg661: =1 for region 1, 1966
reg662: =1 for region 2, 1966
reg663: =1 for region 3, 1966
reg664: =1 for region 4, 1966
reg665: =1 for region 5, 1966
reg666: =1 for region 6, 1966
reg667: =1 for region 7, 1966
reg668: =1 for region 8, 1966
reg669: =1 for region 9, 1966
south66: =1 if in south in 1966
black: =1 if black
smsa: =1 in in SMSA, 1976
south: =1 if in south, 1976
smsa66: =1 if in SMSA, 1966
wage: hourly wage in cents, 1976
enroll: =1 if enrolled in school, 1976
KWW: knowledge world of work score
IQ: IQ score
married: =1 if married, 1976
libcrd14: =1 if lib. card in home at 14
exper: age - educ - 6
lwage: log(wage)
expersq: exper^2
Computer Exercise C15.3 is important for analyzing these data. There, it is shown that the instrumental variable, ‘nearc4', is actually correlated with 'IQ', at least for the subset of men for which an IQ score is reported. However, the correlation between 'nearc4“ and 'IQ', once the other explanatory variables are netted out, is arguably zero. At least, it is not statistically different from zero. In other words, 'nearc4' fails the exogeneity requirement in a simple regression model but it passes, at least using the crude test described above, if controls are added to the wage equation. For a more advanced course, a nice extension of Card’s analysis is to allow the return to education to differ by race. A relatively simple extension is to include black education (blackeduc) as an additional explanatory variable; its natural instrument is blacknearc4.
Used in Text: pages 526-527, 547
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(card)str(card)
Wooldridge Source: Altonji, J.G., T.E. Elder, and C.R. Taber (2005), “An Evaluation of Instrumental Variable Strategies for Estimating the Effects of Catholic Schooling,” Journal of Human Resources 40, 791-821. Professor Elder kindly provided a subset of the data, with some variables stripped away for confidentiality reasons. Data loads lazily.
data('catholic')data('catholic')
A data.frame with 7430 observations on 13 variables:
id: person identifier
read12: reading standardized score
math12: mathematics standardized score
female: =1 if female
asian: =1 if Asian
hispan: =1 if Hispanic
black: =1 if black
motheduc: mother's years of education
fatheduc: father's years of education
lfaminc: log of family income
hsgrad: =1 if graduated from high school by 1994
cathhs: =1 if attended Catholic HS
parcath: =1 if a parent reports being Catholic
pages 267, 551
http://www.cengage.com/c/introductory-econometrics-a-modern-approach-6e-wooldridge
str(catholic)str(catholic)
Wooldridge Source: J. Shea (1993), “The Input-Output Approach to Instrument Selection,” Journal of Business and Economic Statistics 11, 145-156. Professor Shea kindly provided these data. Data loads lazily.
data('cement')data('cement')
A data.frame with 312 observations on 30 variables:
year: 1964-1989
month: 1-12
prccem: BLS ppi for cement
ipcem: industrial prod. index, cement
prcpet: ppi for crude petroleum
rresc: real residential construction
rnonc: real nonres. construction
ip: aggregate index of indus. prod.
rdefs: real defense spending
milemp: military employment
gprc: log(prccem) - log(prccem[_n-1])
gcem: log(ipcem) - log(ipcem[_n-1])
gprcpet: log(prcpet) - log(prcpet[_n-1])
gres: log(rresc) - log(rresc[_n-1])
gnon: log(rnonc) - log(rnonc[_n-1])
gip: log(ip) - log(ip[_n-1])
gdefs: log(rdefs) - log(rdefs[_n-1])
gmilemp: log(milemp) - log(milemp[_n-1])
jan: =1 if month == 1
feb: =1 if month == 2
mar: =1 if month == 3
apr: =1 if month == 4
may: =1 if month == 5
jun: =1 if month == 6
jul: =1 if month == 7
aug: =1 if month == 8
sep: =1 if month == 9
oct: =1 if month == 10
nov: =1 if month == 11
dec: =1 if month == 12
Compared with Shea’s analysis, the producer price index (PPI) for fuels and power has been replaced with the PPI for petroleum. The data are monthly and have not been seasonally adjusted.
Used in Text: pages 579
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(cement)str(cement)
Wooldridge Source: Obtained from the United States Census Bureau by Professor Alberto Abadie of the Harvard Kennedy School of Government. Professor Abadie kindly provided the data. Data loads lazily.
data('census2000')data('census2000')
A data.frame with 29501 observations on 6 variables:
state: State (ICPSR code)
puma: Public Use Microdata Area
educ: educational attainment
lweekinc: log(weekly income)
exper: years workforce experience
expersq: exper^2
pages 452-453
http://www.cengage.com/c/introductory-econometrics-a-modern-approach-6e-wooldridge
str(census2000)str(census2000)
Wooldridge Source: I took a random sample of data reported in the May 6, 1991 issue of Businessweek. Data loads lazily.
data('ceosal1')data('ceosal1')
A data.frame with 209 observations on 12 variables:
salary: 1990 salary, thousands $
pcsalary: percent change salary, 89-90
sales: 1990 firm sales, millions $
roe: return on equity, 88-90 avg
pcroe: percent change roe, 88-90
ros: return on firm's stock, 88-90
indus: =1 if industrial firm
finance: =1 if financial firm
consprod: =1 if consumer product firm
utility: =1 if transport. or utilties
lsalary: natural log of salary
lsales: natural log of sales
This kind of data collection is relatively easy for students just learning data analysis, and the findings can be interesting. A good term project is to have students collect a similar data set using a more recent issue of Businessweek, and to find additional variables that might explain differences in CEO compensation. My impression is that the public is still interested in CEO compensation. An interesting question is whether the list of explanatory variables included in this data set now explain less of the variation in log(salary) than they used to.
Used in Text: pages 32, 35-36, 39, 159-160, 218-219, 260-261, 263, 685, 692-693
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(ceosal1)str(ceosal1)
Wooldridge Source: See CEOSAL1.RAW Data loads lazily.
data('ceosal2')data('ceosal2')
A data.frame with 177 observations on 15 variables:
salary: 1990 compensation, $1000s
age: in years
college: =1 if attended college
grad: =1 if attended graduate school
comten: years with company
ceoten: years as ceo with company
sales: 1990 firm sales, millions
profits: 1990 profits, millions
mktval: market value, end 1990, mills.
lsalary: log(salary)
lsales: log(sales)
lmktval: log(mktval)
comtensq: comten^2
ceotensq: ceoten^2
profmarg: profits as percent of sales
Compared with CEOSAL1.RAW, in this CEO data set more information about the CEO, rather than about the company, is included.
Used in Text: pages 64, 111, 163, 214, 335, 699
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(ceosal2)str(ceosal2)
Wooldridge Source: P.H. Franses and R. Paap (2001), Quantitative Models in Marketing Research. Cambridge: Cambridge University Press. Professor Franses kindly provided the data. Data loads lazily.
data('charity')data('charity')
A data.frame with 4268 observations on 8 variables:
respond: =1 if responded with gift
gift: amount of gift, Dutch guilders
resplast: =1 if responded to most recent mailing
weekslast: number of weeks since last response
propresp: response rate to mailings
mailsyear: number of mailings per year
giftlast: amount of most recent gift
avggift: average of past gifts
This data set can be used to illustrate probit and Tobit models, and to study the linear approximations to them.
Used in Text: pages 65, 112-113, 266-267, 628
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(charity)str(charity)
Wooldridge Source: I collected these data from the 1997 Economic Report of the President. Specifically, the data come from Tables B-71, 15, 29, and 32. Data loads lazily.
data('consump')data('consump')
A data.frame with 37 observations on 24 variables:
year: 1959-1995
i3: 3 mo. T-bill rate
inf: inflation rate; CPI
rdisp: disp. inc., 1992 $, bils.
rnondc: nondur. cons., 1992 $, bils.
rserv: services, 1992 $, bils.
pop: population, 1000s
y: per capita real disp. inc.
rcons: rnondc + rserv
c: per capita real cons.
r3: i3 - inf; real ex post int.
lc: log(c)
ly: log(y)
gc: lc - lc[_n-1]
gy: ly - ly[_n-1]
gc_1: gc[_n-1]
gy_1: gy[_n-1]
r3_1: r3[_n-1]
lc_ly: lc - ly
lc_ly_1: lc_ly[_n-1]
gc_2: gc[_n-2]
gy_2: gy[_n-2]
r3_2: r3[_n-2]
lc_ly_2: lc_ly[_n-2]
For a student interested in time series methods, updating this data set and using it in a manner similar to that in the text could be acceptable as a final project.
Used in Text: pages 377-378, 408-409, 442, 570-571, 579, 673
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(consump)str(consump)
Wooldridge Source: G.E. Battese, R.M. Harter, and W.A. Fuller (1988), “An Error-Components Model for Prediction of County Crop Areas Using Survey and Satellite Data,” Journal of the American Statistical Association 83, 28-36. This small data set is reported in the article. Data loads lazily.
data('corn')data('corn')
A data.frame with 37 observations on 5 variables:
county: county number
cornhec: corn per hectare
soyhec: soybeans per hectare
cornpix: corn pixels per hectare
soypix: soy pixels per hectare
You could use these data to illustrate simple regression when the population intercept should be zero: no corn pixels should predict no corn planted. The same can be done with the soybean measures in the data set.
Used in Text: pages 791-792
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(corn)str(corn)
Wooldridge Source: Compiled by J. Monroe Gamble for a Summer Research Opportunities Program (SROP) at Michigan State University, Summer 2014. Monroe obtained data from the U.S. Census Bureau, the FBI Uniform Crime Reports, and the Death Penalty Information Center. Data loads lazily.
data('countymurders')data('countymurders')
A data.frame with 37349 observations on 20 variables:
arrests: # of murder arrests
countyid: county identifier: 1000*statefips + countyfips
density: population density; per square mile
popul: county population
perc1019: percent pop. age 10-19
perc2029: percent pop. age 20-29
percblack: percent population black
percmale: percent population male
rpcincmaint: real per capita income maintenance
rpcpersinc: real per capita personal income
rpcunemins: real per capita unem insurance payments
year: 1980-1996
murders: # of murders
murdrate: murders per 10,000 people
arrestrate: murder arrests per 10,000
statefips: state FIPS code
countyfips: county FIPS code
execs: # of executions
lpopul: log(popul)
execrate: executions per 10,000
pages 16, 58, 431, 457
http://www.cengage.com/c/introductory-econometrics-a-modern-approach-6e-wooldridge
str(countymurders)str(countymurders)
Wooldridge Source: Professor Henry Farber, now at Princeton University, compiled these data from the 1978 and 1985 Current Population Surveys. Professor Farber kindly provided these data when we were colleagues at MIT. Data loads lazily.
data('cps78_85')data('cps78_85')
A data.frame with 1084 observations on 15 variables:
educ: years of schooling
south: =1 if live in south
nonwhite: =1 if nonwhite
female: =1 if female
married: =1 if married
exper: age - educ - 6
expersq: exper^2
union: =1 if belong to union
lwage: log hourly wage
age: in years
year: 78 or 85
y85: =1 if year == 85
y85fem: y85*female
y85educ: y85*educ
y85union: y85*union
Obtaining more recent data from the CPS allows one to track, over a long period of time, the changes in the return to education, the gender gap, black-white wage differentials, and the union wage premium.
Used in Text: pages 451, 476
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(cps78_85)str(cps78_85)
Wooldridge Source: Professor Daniel Hamermesh, at the University of Texas, compiled these data from the May 1991 Current Population Survey. Professor Hamermesh kindly provided these data. Data loads lazily.
data('cps91')data('cps91')
A data.frame with 5634 observations on 24 variables:
husage: husband's age
husunion: =1 if hus. in union
husearns: hus. weekly earns
huseduc: husband's yrs schooling
husblck: =1 if hus. black
hushisp: =1 if hus. hispanic
hushrs: hus. weekly hours
kidge6: =1 if have child >= 6
earns: wife's weekly earnings
age: wife's age
black: =1 if wife black
educ: wife's yrs schooling
hispanic: =1 if wife hispanic
union: =1 if wife in union
faminc: annual family income
husexp: huseduc - husage - 6
exper: age - educ - 6
kidlt6: =1 if have child < 6
hours: wife's weekly hours
expersq: exper^2
nwifeinc: non-wife inc, $1000s
inlf: =1 if wife in labor force
hrwage: earns/hours
lwage: log(hrwage)
This is much bigger than the other CPS data sets even though the sample is restricted to married women. (CPS91.RAW contains many more observations than MROZ.RAW, too.) In addition to the usual human capital variables for the women in the sample, we have information on the husband. Therefore, we can estimate a labor supply function as in Chapter 16, although the validity of potential experience as an IV for log(wage) is questionable. (MROZ.RAW contains an actual experience variable.) Perhaps more convincing is to add hours to the wage offer equation, and instrument hours with indicators for young and old children. This data set also contains a union membership indicator. The web site for the National Bureau of Economic Research makes it very easy now to download CPS data files in a variety offormats. Go to http://www.nber.org/data/cps_basic.html.
Used in Text: page 627-628
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(cps91)str(cps91)
Wooldridge Source: J. Grogger (1991), “Certainty vs. Severity of Punishment,” Economic Inquiry 29, 297-309. Professor Grogger kindly provided a subset of the data he used in his article. Data loads lazily.
data('crime1')data('crime1')
A data.frame with 2725 observations on 16 variables:
narr86: # times arrested, 1986
nfarr86: # felony arrests, 1986
nparr86: # property crme arr., 1986
pcnv: proportion of prior convictions
avgsen: avg sentence length, mos.
tottime: time in prison since 18 (mos.)
ptime86: mos. in prison during 1986
qemp86: # quarters employed, 1986
inc86: legal income, 1986, $100s
durat: recent unemp duration
black: =1 if black
hispan: =1 if Hispanic
born60: =1 if born in 1960
pcnvsq: pcnv^2
pt86sq: ptime86^2
inc86sq: inc86^2
pages 82-83, 173-174, 180, 252-253, 275, 299, 305-306, 607-608, 625
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(crime1)str(crime1)
Wooldridge Source: These data were collected by David Dicicco, a former MSU undergraduate, for a final project. They came from various issues of the County and City Data Book, and are for the years 1982 and 1985. Unfortunately, I do not have the list of cities. Data loads lazily.
data('crime2')data('crime2')
A data.frame with 92 observations on 34 variables:
pop: population
crimes: total number index crimes
unem: unemployment rate
officers: number police officers
pcinc: per capita income
west: =1 if city in west
nrtheast: =1 if city in NE
south: =1 if city in south
year: 82 or 87
area: land area, square miles
d87: =1 if year = 87
popden: people per sq mile
crmrte: crimes per 1000 people
offarea: officers per sq mile
lawexpc: law enforce. expend. pc, $
polpc: police per 1000 people
lpop: log(pop)
loffic: log(officers)
lpcinc: log(pcinc)
llawexpc: log(lawexpc)
lpopden: log(popden)
lcrimes: log(crimes)
larea: log(area)
lcrmrte: log(crmrte)
clcrimes: change in lcrimes
clpop: change in lpop
clcrmrte: change in lcrmrte
lpolpc: log(polpc)
clpolpc: change in lpolpc
cllawexp: change in llawexp
cunem: change in unem
clpopden: change in lpopden
lcrmrt_1: lcrmrte lagged
ccrmrte: change in crmrte
Very rich crime data sets, at the county, or even city, level, can be collected using the FBI’s Uniform Crime Reports. These data can be matched up with demographic and economic data, at least for census years. The County and City Data Book contains a variety of statistics, but the years do not always match up. These data sets can be used investigate issues such as the effects of casinos on city or county crime rates.
Used in Text: pages 313-314, 459-460
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(crime2)str(crime2)
Wooldridge Source: E. Eide (1994), Economics of Crime: Deterrence of the Rational Offender. Amsterdam: North Holland. The data come from Tables A3 and A6. Data loads lazily.
data('crime3')data('crime3')
A data.frame with 106 observations on 12 variables:
district: district number
year: 72 or 78
crime: crimes per 1000 people
clrprc1: clear-up perc, prior year
clrprc2: clear-up perc, two-years prior
d78: =1 if year = 78
avgclr: (clrprc1 + clrprc2)/2
lcrime: log(crime)
clcrime: change in lcrime
cavgclr: change in avgclr
cclrprc1: change in clrprc1
cclrprc2: change in clrprc2
These data are for the years 1972 and 1978 for 53 police districts in Norway. Much larger data sets for more years can be obtained for the United States, although a measure of the “clear-up” rate is needed.
Used in Text: pages 464-465, 477-478
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(crime3)str(crime3)
Wooldridge Source: From C. Cornwell and W. Trumball (1994), “Estimating the Economic Model of Crime with Panel Data,” Review of Economics and Statistics 76, 360-366. Professor Cornwell kindly provided the data. Data loads lazily.
data('crime4')data('crime4')
A data.frame with 630 observations on 59 variables:
county: county identifier
year: 81 to 87
crmrte: crimes committed per person
prbarr: 'probability' of arrest
prbconv: 'probability' of conviction
prbpris: 'probability' of prison sentenc
avgsen: avg. sentence, days
polpc: police per capita
density: people per sq. mile
taxpc: tax revenue per capita
west: =1 if in western N.C.
central: =1 if in central N.C.
urban: =1 if in SMSA
pctmin80: perc. minority, 1980
wcon: weekly wage, construction
wtuc: wkly wge, trns, util, commun
wtrd: wkly wge, whlesle, retail trade
wfir: wkly wge, fin, ins, real est
wser: wkly wge, service industry
wmfg: wkly wge, manufacturing
wfed: wkly wge, fed employees
wsta: wkly wge, state employees
wloc: wkly wge, local gov emps
mix: offense mix: face-to-face/other
pctymle: percent young male
d82: =1 if year == 82
d83: =1 if year == 83
d84: =1 if year == 84
d85: =1 if year == 85
d86: =1 if year == 86
d87: =1 if year == 87
lcrmrte: log(crmrte)
lprbarr: log(prbarr)
lprbconv: log(prbconv)
lprbpris: log(prbpris)
lavgsen: log(avgsen)
lpolpc: log(polpc)
ldensity: log(density)
ltaxpc: log(taxpc)
lwcon: log(wcon)
lwtuc: log(wtuc)
lwtrd: log(wtrd)
lwfir: log(wfir)
lwser: log(wser)
lwmfg: log(wmfg)
lwfed: log(wfed)
lwsta: log(wsta)
lwloc: log(wloc)
lmix: log(mix)
lpctymle: log(pctymle)
lpctmin: log(pctmin)
clcrmrte: lcrmrte - lcrmrte[_n-1]
clprbarr: lprbarr - lprbarr[_n-1]
clprbcon: lprbconv - lprbconv[_n-1]
clprbpri: lprbpri - lprbpri[t-1]
clavgsen: lavgsen - lavgsen[t-1]
clpolpc: lpolpc - lpolpc[t-1]
cltaxpc: ltaxpc - ltaxpc[t-1]
clmix: lmix - lmix[t-1]
Computer Exercise C16.7 shows that variables that might seem to be good instrumental variable candidates are not always so good, especially after applying a transformation such as differencing across time. You could have the students do an IV analysis for just, say, 1987.
Used in Text: pages 471-472, 479, 504, 580
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(crime4)str(crime4)
Wooldridge Source: K. Graddy (1997), “Do Fast-Food Chains Price Discriminate on the Race and Income Characteristics of an Area?” Journal of Business and Economic Statistics 15, 391-401. Professor Graddy kindly provided the data set. Data loads lazily.
data('discrim')data('discrim')
A data.frame with 410 observations on 37 variables:
psoda: price of medium soda, 1st wave
pfries: price of small fries, 1st wave
pentree: price entree (burger or chicken), 1st wave
wagest: starting wage, 1st wave
nmgrs: number of managers, 1st wave
nregs: number of registers, 1st wave
hrsopen: hours open, 1st wave
emp: number of employees, 1st wave
psoda2: price of medium soday, 2nd wave
pfries2: price of small fries, 2nd wave
pentree2: price entree, 2nd wave
wagest2: starting wage, 2nd wave
nmgrs2: number of managers, 2nd wave
nregs2: number of registers, 2nd wave
hrsopen2: hours open, 2nd wave
emp2: number of employees, 2nd wave
compown: =1 if company owned
chain: BK = 1, KFC = 2, Roy Rogers = 3, Wendy's = 4
density: population density, town
crmrte: crime rate, town
state: NJ = 1, PA = 2
prpblck: proportion black, zipcode
prppov: proportion in poverty, zipcode
prpncar: proportion no car, zipcode
hseval: median housing value, zipcode
nstores: number of stores, zipcode
income: median family income, zipcode
county: county label
lpsoda: log(psoda)
lpfries: log(pfries)
lhseval: log(hseval)
lincome: log(income)
ldensity: log(density)
NJ: =1 for New Jersey
BK: =1 if Burger King
KFC: =1 if Kentucky Fried Chicken
RR: =1 if Roy Rogers
If you want to assign a common final project, this would be a good data set. There are many possible dependent variables, namely, prices of various fast-food items. The key variable is the fraction of the population that is black, along with controls for poverty, income, housing values, and so on. These data were also used in a famous study by David Card and Alan Krueger on estimation of minimum wage effects on employment. See the book by Card and Krueger, Myth and Measurement, 1997, Princeton University Press, for a detailed analysis.
Used in Text: pages 112, 166, 699-700
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(discrim)str(discrim)
Wooldridge Source: Freeman, D.G. (2007), “Drunk Driving Legislation and Traffic Fatalities: New Evidence on BAC 08 Laws,” Contemporary Economic Policy 25, 293–308. Professor Freeman kindly provided the data. Data loads lazily.
data('driving')data('driving')
A data.frame with 1200 observations on 56 variables:
year: 1980 through 2004
state: 48 continental states, alphabetical
sl55: speed limit == 55
sl65: speed limit == 65
sl70: speed limit == 70
sl75: speed limit == 75
slnone: no speed limit
seatbelt: =0 if none, =1 if primary, =2 if secondary
minage: minimum drinking age
zerotol: zero tolerance law
gdl: graduated drivers license law
bac10: blood alcohol limit .10
bac08: blood alcohol limit .08
perse: administrative license revocation (per se law)
totfat: total traffic fatalities
nghtfat: total nighttime fatalities
wkndfat: total weekend fatalities
totfatpvm: total fatalities per 100 million miles
nghtfatpvm: nighttime fatalities per 100 million miles
wkndfatpvm: weekend fatalities per 100 million miles
statepop: state population
totfatrte: total fatalities per 100,000 population
nghtfatrte: nighttime fatalities per 100,000 population
wkndfatrte: weekend accidents per 100,000 population
vehicmiles: vehicle miles traveled, billions
unem: unemployment rate, percent
perc14_24: percent population aged 14 through 24
sl70plus: sl70 + sl75 + slnone
sbprim: =1 if primary seatbelt law
sbsecon: =1 if secondary seatbelt law
d80: =1 if year == 1980
d81:
d82:
d83:
d84:
d85:
d86:
d87:
d88:
d89:
d90:
d91:
d92:
d93:
d94:
d95:
d96:
d97:
d98:
d99:
d00:
d01:
d02:
d03:
d04: =1 if year == 2004
vehicmilespc:
Several more years of data are available and may further shed light on the effectiveness of several traffic laws.
Used in Text: not used, but see page 695
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(driving)str(driving)
Wooldridge Source: Economic Report of the President, 1989, Table B-47. The data are for the non-farm business sector. Data loads lazily.
data('earns')data('earns')
A data.frame with 41 observations on 14 variables:
year: 1947 to 1987
wkearns: avg. real weekly earnings
wkhours: avg. weekly hours
outphr: output per labor hour
hrwage: wkearns/wkhours
lhrwage: log(hrwage)
loutphr: log(outphr)
t: time trend: t=1 to 47
ghrwage: lhrwage - lhrwage[_n-1]
goutphr: loutphr - loutphr[_n-1]
ghrwge_1: ghrwage[_n-1]
goutph_1: goutphr[_n-1]
goutph_2: goutphr[_n-2]
lwkhours: log(wkhours)
These data could be usefully updated, but changes in reporting conventions in more recent ERPs may make that difficult.
Used in Text: pages 363-364, 398, 407
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(earns)str(earns)
Wooldridge Source: Compiled by Professor Charles Ballard, Michigan State University Department of Economics. Professor Ballard kindly provided the data. Data loads lazily.
data('econmath')data('econmath')
A data.frame with 856 observations on 17 variables:
age: age in years
work: hours worked per week
study: hours studying per week
econhs: =1 if economics in high school
colgpa: college GPA, beginning semester
hsgpa: high school GPA
acteng: ACT English score
actmth: ACT math score
act: ACT composite
mathscr: math quiz score, 0-10
male: =1 if male
calculus: =1 if taken calculus course
attexc: =1 if past attndce 'excellent'
attgood: =1 if past attndce 'good'
fathcoll: =1 if father has BA
mothcoll: =1 if mother has BA
score: course score, in percent
167, 185
http://www.cengage.com/c/introductory-econometrics-a-modern-approach-6e-wooldridge
str(econmath)str(econmath)
Wooldridge Source: Culled from a panel data set used by Leslie Papke in her paper “The Effects of Spending on Test Pass Rates: Evidence from Michigan” (2005), Journal of Public Economics 89, 821-839. Data loads lazily.
data('elem94_95')data('elem94_95')
A data.frame with 1848 observations on 14 variables:
distid: district identifier
schid: school identifier
lunch: percent eligible, free lunch
enrol: enrollment
staff: staff per 1000 students
exppp: expenditures per pupil
avgsal: average teacher salary, $
avgben: average teacher non-salary benefits, $
math4: percent passing 4th grade math test
story4: percent passing 4th grade reading test
bs: avgben/avgsal
lavgsal: log(avgsal)
lenrol: log(enrol)
lstaff: log(staff)
Starting in 1995, the Michigan Department of Education stopped reporting average teacher benefits along with average salary. This data set includes both variables, at the school level, and can be used to study the salary-benefits tradeoff, as in Chapter 4. There are a few suspicious benefits/salary ratios, and so this data set makes a good illustration of the impact of outliers in Chapter 9.
Used in Text: pages 166-167, 341-342
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(elem94_95)str(elem94_95)
Wooldridge Source: Thada Chaisawangwong, a former graduate student at MSU, obtained these data for a term project in applied econometrics. They come from the Material Requirement Planning Survey carried out in Thailand during 1998. Data loads lazily.
data('engin')data('engin')
A data.frame with 403 observations on 17 variables:
male: =1 if male
educ: highest grade completed
wage: monthly salary, Thai baht
swage: starting wage
exper: years on current job
pexper: previous experience
lwage: log(wage)
expersq: exper^2
highgrad: =1 if high school graduate
college: =1 if college graduate
grad: =1 if some graduate school
polytech: =1 if a polytech
highdrop: =1 if no high school degree
lswage: log(swage)
pexpersq: pexper^2
mleeduc: male*educ
mleeduc0: male*(educ - 14)
This is a nice change of pace from wage data sets for the United States. These data are for engineers in Thailand, and represents a more homogeneous group than data sets that consist of people across a variety of occupations. Plus, the starting salary is also provided in the data set, so factors affecting wage growth – and not just wage levels at a given point in time – can be studied. This is a good data set for a common term project that tests basic understanding of multiple regression and the interpretation of models with a logarithm for a dependent variable.
Used in Text: not used
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(engin)str(engin)
Wooldridge Source: L.E. Papke (1994), “Tax Policy and Urban Development: Evidence from the Indiana Enterprise Zone Program,” Journal of Public Economics 54, 37-49. Professor Papke kindly provided these data. Data loads lazily.
data('ezanders')data('ezanders')
A data.frame with 108 observations on 25 variables:
month: name of month
uclms: unemployment claims
ez: =1 if enterprise zone
year: 1980 through 1988
y81: =1 if year == 1981
y82:
y83:
y84:
y85:
y86:
y87:
y88:
luclms: log(uclms)
jan: =1 if month == JAN
feb:
mar:
apr:
may:
jun:
jul:
aug:
sep:
oct:
nov:
dec:
These are actually monthly unemployment claims for the Anderson enterprise zone. Papke used annualized data, across many zones and non-zones, in her original analysis.
Used in Text: page 377
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(ezanders)str(ezanders)
Wooldridge Source: See EZANDERS.RAW Data loads lazily.
data('ezunem')data('ezunem')
A data.frame with 198 observations on 37 variables:
year: 1980 to 1988
uclms: unemployment claims
ez: =1 if have enterprise zone
d81: =1 if year == 1981
d82: =1 if year == 1982
d83: =1 if year == 1983
d84: =1 if year == 1984
d85: =1 if year == 1985
d86: =1 if year == 1986
d87: =1 if year == 1987
d88: =1 if year == 1988
c1: =1 if city == 1
c2: =1 if city == 2
c3: =1 if city == 3
c4:
c5:
c6:
c7:
c8:
c9:
c10:
c11:
c12:
c13:
c14:
c15:
c16:
c17:
c18:
c19:
c20:
c21:
c22: =1 if city == 22
luclms: log(uclms)
guclms: luclms - luclms[_n-1]
cez: ez - ez[_n-1]
city: city identifier, 1 through 22
A very good project is to have students analyze enterprise, empowerment, or renaissance zone policies in their home states. Many states now have such programs. A few years of panel data straddling periods of zone designation, at the city or zip code level, could make a nice study.
Used in Text: pages 470, 504
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(ezunem)str(ezunem)
Wooldridge Source: R.C. Fair (1996), “Econometrics and Presidential Elections,” Journal of Economic Perspectives 10, 89-102. The data set is provided in the article. Data loads lazily.
data('fair')data('fair')
A data.frame with 21 observations on 28 variables:
year: 1916 to 1992, by 4
V: prop. dem. vote
I: =1 if demwh, -1 if repwh
DPER: incumbent running
DUR: duration
g3: avg ann grwth rte, prev 3 qrts
p15: avg ann inf rate, prev 15 qtrs
n: quarters of good news
g2: avg ann grwth rte, prev 2 qrts
gYR: ann grwth rte, prev year
p8: avg ann inf rate, prev 8 qtrs
p2YR: inf rte over 2 yr period
Ig2: I*g2
Ip8: I*p8
demwins: =1 if V > .5
In: I*n
d: =1 in 1920, 1944,1948
Id: I*d
Ig3: I*g3
Ip151md: I*p15*(1-d)
In1md: I*n*(1-d)
An updated version of this data set, through the 2004 election, is available at Professor Fair’s web site at Yale University: http://fairmodel.econ.yale.edu/rayfair/pdf/2001b.htm. Students might want to try their own hands at predicting the most recent election outcome, but they should be restricted to no more than a handful of explanatory variables because of the small sample size.
Used in Text: pages 362-363, 440, 442
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(fair)str(fair)
Wooldridge Source: W. Sander, “The Effect of Women’s Schooling on Fertility,” Economics Letters 40, 229-233.Professor Sander kindly provided the data, which are a subset of what he used in his article. He compiled the data from various years of the National Opinion Resource Center’s General Social Survey. Data loads lazily.
data('fertil1')data('fertil1')
A data.frame with 1129 observations on 27 variables:
year: 72 to 84, even
educ: years of schooling
meduc: mother's education
feduc: father's education
age: in years
kids: # children ever born
black: = 1 if black
east: = 1 if lived in east at 16
northcen: = 1 if lived in nc at 16
west: = 1 if lived in west at 16
farm: = 1 if on farm at 16
othrural: = 1 if other rural at 16
town: = 1 if lived in town at 16
smcity: = 1 if in small city at 16
y74: = 1 if year = 74
y76:
y78:
y80:
y82:
y84:
agesq: age^2
y74educ:
y76educ:
y78educ:
y80educ:
y82educ:
y84educ:
(1) Much more recent data can be obtained from the National Opinion Research Center website, http://www.norc.org/GSS+Website/Download/. Very rich pooled cross sections can be constructed to study a variety of issues – not just changes in fertility over time. It would be interesting to analyze a similar data set for a developing country, especially where efforts have been made to emphasize birth control. Some measure of access to birth control could be useful if it varied by region. Sometimes, one can find policy changes in the advertisement or availability of contraceptives.
Used in Text: pages 449-450, 476, 541, 625, 681
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(fertil1)str(fertil1)
Wooldridge Source: These data were obtained by James Heakins, a former MSU undergraduate, for a term project. They come from Botswana’s 1988 Demographic and Health Survey. Data loads lazily.
data('fertil2')data('fertil2')
A data.frame with 4361 observations on 27 variables:
mnthborn: month woman born
yearborn: year woman born
age: age in years
electric: =1 if has electricity
radio: =1 if has radio
tv: =1 if has tv
bicycle: =1 if has bicycle
educ: years of education
ceb: children ever born
agefbrth: age at first birth
children: number of living children
knowmeth: =1 if know about birth control
usemeth: =1 if ever use birth control
monthfm: month of first marriage
yearfm: year of first marriage
agefm: age at first marriage
idlnchld: 'ideal' number of children
heduc: husband's years of education
agesq: age^2
urban: =1 if live in urban area
urb_educ: urban*educ
spirit: =1 if religion == spirit
protest: =1 if religion == protestant
catholic: =1 if religion == catholic
frsthalf: =1 if mnthborn <= 6
educ0: =1 if educ == 0
evermarr: =1 if ever married
Currently, this data set is used only in one computer exercise. Since the dependent variable of interest – number of living children or number of children every born – is a count variable, the Poisson regression model discussed in Chapter 17 can be used. However, some care is required to combine Poisson regression with an endogenous explanatory variable (educ). I refer you to Chapter 19 of my book Econometric Analysis of Cross Section and Panel Data. Even in the context of linear models, much can be done beyond Computer Exercise C15.2. At a minimum, the binary indicators for various religions can be added as controls. One might also interact the schooling variable, educ, with some of the exogenous explanatory variables.
Used in Text: page 547
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(fertil2)str(fertil2)
Wooldridge Source: L.A. Whittington, J. Alm, and H.E. Peters (1990), “Fertility and the Personal Exemption: Implicit Pronatalist Policy in the United States,” American Economic Review 80, 545-556. The data are given in the article. Data loads lazily.
data('fertil3')data('fertil3')
A data.frame with 72 observations on 24 variables:
gfr: births per 1000 women 15-44
pe: real value pers. exemption, $
year: 1913 to 1984
t: time trend, t=1,...,72
tsq: t^2
pe_1: pe[_n-1]
pe_2: pe[_n-2]
pe_3: pe[_n-3]
pe_4: pe[_n-4]
pill: =1 if year >= 1963
ww2: =1, 1941 to 1945
tcu: t^3
cgfr: change in gfr: gfr - gfr_1
cpe: pe - pe_1
cpe_1: cpe[_n-1]
cpe_2: cpe[_n-2]
cpe_3: cpe[_n-3]
cpe_4: cpe[_n-4]
gfr_1: gfr[_n-1]
cgfr_1: cgfr[_n-1]
cgfr_2: cgfr[_n-2]
cgfr_3: cgfr[_n-3]
cgfr_4: cgfr[_n-4]
gfr_2: gfr[_n-2]
pages 358, 377, 378, 397-398, 401, 408, 441, 649, 664-665, 673
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(fertil3)str(fertil3)
Wooldridge Source: K Graddy (1995), “Testing for Imperfect Competition at the Fulton Fish Market,” RAND Journal of Economics 26, 75-92. Professor Graddy's collaborator on a later paper, Professor Joshua Angrist at MIT, kindly provided me with these data. Data loads lazily.
data('fish')data('fish')
A data.frame with 97 observations on 20 variables:
prca: price for Asian buyers
prcw: price for white buyers
qtya: quantity sold to Asians
qtyw: quantity sold to whites
mon: =1 if Monday
tues: =1 if Tuesday
wed: =1 if Wednesday
thurs: =1 if Thursday
speed2: min past 2 days wind speeds
wave2: avg max last 2 days wave height
speed3: 3 day lagged max windspeed
wave3: avg max wave hghts of 3 & 4 day lagged hghts
avgprc: ((prca*qtya) + (prcw*qtyw))/(qtya + qtyw)
totqty: qtya + qtyw
lavgprc: log(avgprc)
ltotqty: log(totqty)
t: time trend
lavgp_1: lavgprc[_n-1]
gavgprc: lavgprc - lavgp_1
gavgp_1: gavgprc[_n-1]
This is a nice example of how to go about finding exogenous variables to use as instrumental variables. Often, weather conditions can be assumed to affect supply while having a negligible effect on demand. If so, the weather variables are valid instrumental variables for price in the demand equation. It is a simple matter to test whether prices vary with weather conditions by estimating the reduced form for price.
Used in Text: pages 443, 580
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(fish)str(fish)
Wooldridge Source: F. Vella (1993), “A Simple Estimator for Simultaneous Models with Censored Endogenous Regressors,” International Economic Review 34, 441-457. Professor Vella kindly provided the data. Data loads lazily.
data('fringe')data('fringe')
A data.frame with 616 observations on 39 variables:
annearn: annual earnings, $
hrearn: hourly earnings, $
exper: years work experience
age: age in years
depends: number of dependents
married: =1 if married
tenure: years with current employer
educ: years schooling
nrtheast: =1 if live in northeast
nrthcen: =1 if live in north central
south: =1 if live in south
male: =1 if male
white: =1 if white
union: =1 if union member
office:
annhrs: annual hours worked
ind1: industry dummy
ind2:
ind3:
ind4:
ind5:
ind6:
ind7:
ind8:
ind9:
vacdays: $ value of vac. days
sicklve: $ value of sick leave
insur: $ value of employee insur
pension: $ value of employee pension
annbens: vacdays+sicklve+insur+pension
hrbens: hourly benefits, $
annhrssq: annhrs^2
beratio: annbens/annearn
lannhrs: log(annhrs)
tenuresq: tenure^2
expersq: exper^2
lannearn: log(annearn)
peratio: pension/annearn
vserat: (vacdays+sicklve)/annearn
Currently, this data set is used in only one Computer Exercise – to illustrate the Tobit model. It can be used much earlier. First, one could just ignore the pileup at zero and use a linear model where any of the hourly benefit measures is the dependent variable. Another possibility is to use this data set for a problem set in Chapter 4, after students have read Example 4.10. That example, which uses teacher salary/benefit data at the school level, finds the expected tradeoff, although it appears to less than one-to-one. By contrast, if you do a similar analysis with FRINGE.RAW, you will not find a tradeoff. A positive coefficient on the benefit/salary ratio is not too surprising because we probably cannot control for enough factors, especially when looking across different occupations. The Michigan school-level data is more aggregated than one would like, but it does restrict attention to a more homogeneous group: high school teachers in Michigan.
Used in Text: page 624-625
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(fringe)str(fringe)
Wooldridge Source: Christopher Lemmon, a former MSU undergraduate, collected these data from a survey he took of MSU students in Fall 1994. Data loads lazily.
data('gpa1')data('gpa1')
A data.frame with 141 observations on 29 variables:
age: in years
soph: =1 if sophomore
junior: =1 if junior
senior: =1 if senior
senior5: =1 if fifth year senior
male: =1 if male
campus: =1 if live on campus
business: =1 if business major
engineer: =1 if engineering major
colGPA: MSU GPA
hsGPA: high school GPA
ACT: 'achievement' score
job19: =1 if job <= 19 hours
job20: =1 if job >= 20 hours
drive: =1 if drive to campus
bike: =1 if bicycle to campus
walk: =1 if walk to campus
voluntr: =1 if do volunteer work
PC: =1 of pers computer at sch
greek: =1 if fraternity or sorority
car: =1 if own car
siblings: =1 if have siblings
bgfriend: =1 if boy- or girlfriend
clubs: =1 if belong to MSU club
skipped: avg lectures missed per week
alcohol: avg # days per week drink alc.
gradMI: =1 if Michigan high school
fathcoll: =1 if father college grad
mothcoll: =1 if mother college grad
This is a nice example of how students can obtain an original data set by focusing locally and carefully composing a survey.
Used in Text: pages 75, 77, 81, 129-130, 160, 232, 262, 295-296, 300-301
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(gpa1)str(gpa1)
Wooldridge Source: For confidentiality reasons, I cannot provide the source of these data. I can say that Data loads lazily.
data('gpa2')data('gpa2')
A data.frame with 4137 observations on 12 variables:
sat: combined SAT score
tothrs: total hours through fall semest
colgpa: GPA after fall semester
athlete: =1 if athlete
verbmath: verbal/math SAT score
hsize: size grad. class, 100s
hsrank: rank in grad. class
hsperc: high school percentile, from top
female: =1 if female
white: =1 if white
black: =1 if black
hsizesq: hsize^2
pages 106, 184, 208-209, 210-211, 221, 259, 262-263
they come from a midsize research university that also supports men’s and women’s athletics at the Division I level.
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(gpa2)str(gpa2)
Wooldridge Source: See GPA2.RAW Data loads lazily.
data('gpa3')data('gpa3')
A data.frame with 732 observations on 23 variables:
term: fall = 1, spring = 2
sat: SAT score
tothrs: total hours prior to term
cumgpa: cumulative GPA
season: =1 if in season
frstsem: =1 if student's 1st semester
crsgpa: weighted course GPA
verbmath: verbal SAT to math SAT ratio
trmgpa: term GPA
hssize: size h.s. grad. class
hsrank: rank in h.s. class
id: student identifier
spring: =1 if spring term
female: =1 if female
black: =1 if black
white: =1 if white
ctrmgpa: change in trmgpa
ctothrs: change in total hours
ccrsgpa: change in crsgpa
ccrspop: change in crspop
cseason: change in season
hsperc: percentile in h.s.
football: =1 if football player
pages 246-248, 273, 297-298, 478
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(gpa3)str(gpa3)
Wooldridge Data loads lazily.
data('happiness')data('happiness')
A data.frame with 17137 observations on 33 variables:
year: gss year for this respondent
workstat: work force status
prestige: occupational prestige score
divorce: ever been divorced or separated
widowed: ever been widowed
educ: highest year of school completed
reg16: region of residence, age 16
babies: household members less than 6 yrs old
preteen: household members 6 thru 12 yrs old
teens: household members 13 thru 17 yrs old
income: total family income
region: region of interview
attend: how often r attends religious services
happy: general happiness
owngun: =1 if own gun
tvhours: hours per day watching tv
vhappy: =1 if 'very happy'
mothfath16: =1 if live with mother and father at 16
black: =1 if black
gwbush04: =1 if voted for G.W. Bush in 2004
female: =1 if female
blackfemale: black*female
gwbush00: =1 if voted for G.W. Bush in 2000
occattend: =1 if attend is 3, 4, or 5
regattend: =1 if attend is 6, 7, or 8
y94: =1 if year == 1994
y96:
y98:
y00:
y02:
y04:
y06: =1 if year == 2006
unem10: =1 if unemployed in last 10 years
NA
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(happiness)str(happiness)
Wooldridge Source: Collected from the real estate pages of the Boston Globe during 1990. These are homes that sold in the Boston, MA area. Data loads lazily.
data('hprice1')data('hprice1')
A data.frame with 88 observations on 10 variables:
price: house price, $1000s
assess: assessed value, $1000s
bdrms: number of bdrms
lotsize: size of lot in square feet
sqrft: size of house in square feet
colonial: =1 if home is colonial style
lprice: log(price)
lassess: log(assess
llotsize: log(lotsize)
lsqrft: log(sqrft)
Typically, it is very easy to obtain data on selling prices and characteristics of homes, using publicly available data bases. It is interesting to match the information on houses with other information – such as local crime rates, quality of the local schools, pollution levels, and so on – and estimate the effects of such variables on housing prices.
Used in Text: pages 110, 153-154, 160-161, 165, 211-212, 221, 222, 234, 278, 280, 299, 307
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(hprice1)str(hprice1)
Wooldridge Source: D. Harrison and D.L. Rubinfeld (1978), “Hedonic Housing Prices and the Demand for Clean Air,” by Harrison, D. and D.L.Rubinfeld, Journal of Environmental Economics and Management 5, 81-102. Diego Garcia, a former Ph.D. student in economics at MIT, kindly provided these data, which he obtained from the book Regression Diagnostics: Identifying Influential Data and Sources of Collinearity, by D.A. Belsey, E. Kuh, and R. Welsch, 1990. New York: Wiley. Data loads lazily.
data('hprice2')data('hprice2')
A data.frame with 506 observations on 12 variables:
price: median housing price, $
crime: crimes committed per capita
nox: nit ox concen; parts per 100m
rooms: avg number of rooms
dist: wght dist to 5 employ centers
radial: access. index to rad. hghwys
proptax: property tax per $1000
stratio: average student-teacher ratio
lowstat: perc of people 'lower status'
lprice: log(price)
lnox: log(nox)
lproptax: log(proptax)
The census contains rich information on variables such as median housing prices, median income levels, average family size, and so on, for fairly small geographical areas. If such data can be merged with pollution data, one can update the Harrison and Rubinfeld study. Presumably, this has been done in academic journals.
Used in Text: pages 108, 132-133, 190-191, 196-197.
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(hprice2)str(hprice2)
Wooldridge Data loads lazily.
data('hprice3')data('hprice3')
A data.frame with 321 observations on 19 variables:
year: 1978, 1981
age: age of house
agesq: age^2
nbh: neighborhood, 1-6
cbd: dist. to cent. bus. dstrct, ft.
inst: dist. to interstate, ft.
linst: log(inst)
price: selling price
rooms: # rooms in house
area: square footage of house
land: square footage lot
baths: # bathrooms
dist: dist. from house to incin., ft.
ldist: log(dist)
lprice: log(price)
y81: =1 if year = 1981
larea: log(area)
lland: log(land)
linstsq: linst^2
NA
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(hprice3)str(hprice3)
Wooldridge Source: D. McFadden (1994), “Demographics, the Housing Market, and the Welfare of the Elderly,” in D.A. Wise (ed.), Studies in the Economics of Aging. Chicago: University of Chicago Press, 225-285. The data are contained in the article. Data loads lazily.
data('hseinv')data('hseinv')
A data.frame with 42 observations on 14 variables:
year: 1947-1988
inv: real housing inv, millions $
pop: population, 1000s
price: housing price index; 1982 = 1
linv: log(inv)
lpop: log(pop)
lprice: log(price)
t: time trend: t=1,...,42
invpc: per capita inv: inv/pop
linvpc: log(invpc)
lprice_1: lprice[_n-1]
linvpc_1: linvpc[_n-1]
gprice: lprice - lprice_1
ginvpc: linvpc - linvpc_1
pages 367, 370, 407, 638-639, 822?
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(hseinv)str(hseinv)
Wooldridge Source: J.J. Heckman, J.L. Tobias, and E. Vytlacil (2003), “Simple Estimators for Treatment Parameters in a Latent-Variable Framework,” Review of Economics and Statistics 85, 748-755. Professor Tobias kindly provided the data, which were obtained from the 1991 National Longitudinal Survey of Youth. All people in the sample are males age 26 to 34. For confidentiality reasons, I have included only a subset of the variables used by the authors. Data loads lazily.
data('htv')data('htv')
A data.frame with 1230 observations on 23 variables:
wage: hourly wage, 1991
abil: abil. measure, not standardized
educ: highest grade completed by 1991
ne: =1 if in northeast, 1991
nc: =1 if in nrthcntrl, 1991
west: =1 if in west, 1991
south: =1 if in south, 1991
exper: potential experience
motheduc: highest grade, mother
fatheduc: highest grade, father
brkhme14: =1 if broken home, age 14
sibs: number of siblings
urban: =1 if in urban area, 1991
ne18: =1 if in NE, age 18
nc18: =1 if in NC, age 18
south18: =1 if in south, age 18
west18: =1 if in west, age 18
urban18: =1 if in urban area, age 18
tuit17: college tuition, age 17
tuit18: college tuition, age 18
lwage: log(wage)
expersq: exper^2
ctuit: tuit18 - tuit17
Because an ability measure is included in this data set, it can be used as another illustration of including proxy variables in regression models. See Chapter 9. Also, one can try the IV procedure with the ability measure included as an exogenous explanatory variable.
Used in Text: pages 550, 628
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(htv)str(htv)
Wooldridge Source: Statistical Abstract of the United States, 1990 and 1994. (For example, the infant mortality rates come from Table 113 in 1990 and Table 123 in 1994.) Data loads lazily.
data('infmrt')data('infmrt')
A data.frame with 102 observations on 12 variables:
year: 1987 or 1990
infmort: deaths per 1,000 live births
afdcprt: afdc partic., 1000s
popul: population, 1000s
pcinc: per capita income
physic: drs. per 100,000 civilian pop.
afdcper: percent on AFDC
d90: =1 if year == 1990
lpcinc: log(pcinc)
lphysic: log(physic)
DC: =1 for Washington DC
lpopul: log(popul)
An interesting exercise is to add the percentage of the population on AFDC (afdcper) to the infant mortality equation. Pooled OLS and first differencing can give very different estimates. Adding the years 1998 and 2002 and applying fixed effects seems natural. Intervening years can be added, too, although variation in the key variables from year to year might be minimal.
Used in Text: pages 330-331, 339
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(infmrt)str(infmrt)
Wooldridge Source: B.D. Meyer, W.K. Viscusi, and D.L. Durbin (1995), “Workers’ Compensation and Injury Duration: Evidence from a Natural Experiment,” American Economic Review 85, 322-340. Professor Meyer kindly provided the data. Data loads lazily.
data('injury')data('injury')
A data.frame with 7150 observations on 30 variables:
durat: duration of benefits
afchnge: =1 if after change in benefits
highearn: =1 if high earner
male: =1 if male
married: =1 if married
hosp: =1 if inj. required hosp. stay
indust: industry
injtype: type of injury
age: age at time of injury
prewage: previous weekly wage, 1982 $
totmed: total med. costs, 1982 $
injdes: 4 digit injury description
benefit: real dollar value of benefit
ky: =1 for kentucky
mi: =1 for michigan
ldurat: log(durat)
afhigh: afchnge*highearn
lprewage: log(wage)
lage: log(age)
ltotmed: log(totmed); = 0 if totmed < 1
head: =1 if head injury
neck: =1 if neck injury
upextr: =1 if upper extremities injury
trunk: =1 if trunk injury
lowback: =1 if lower back injury
lowextr: =1 if lower extremities injury
occdis: =1 if occupational disease
manuf: =1 if manufacturing industry
construc: =1 if construction industry
highlpre: highearn*lprewage
This data set also can be used to illustrate the Chow test in Chapter 7. In particular, students can test whether the regression functions differ between Kentucky and Michigan. Or, allowing for different intercepts for the two states, do the slopes differ? A good lesson from this example is that a small R-squared is compatible with the ability to estimate the effects of a policy. Of course, for the Michigan data, which has a smaller sample size, the estimated effect is much less precise (but of virtually identical magnitude).
Used in Text: pages 458-459, 475-476
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(injury)str(injury)
Wooldridge Source: Economic Report of the President, 2004, Tables B-64, B-73, and B-79. Data loads lazily.
data('intdef')data('intdef')
A data.frame with 56 observations on 13 variables:
year: 1948 to 2003
i3: 3 month T-bill rate
inf: CPI inflation rate
rec: federal receipts, percent GDP
out: federal outlays, percent GDP
def: out - rec
i3_1: i3[_n-1]
inf_1: inf[_n-1]
def_1: def[_n-1]
ci3: i3 - i3_1
cinf: inf - inf_1
cdef: def - def_1
y77: =1 if year >= 1977; change in FY
pages 356, 377, 430, 547-548
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(intdef)str(intdef)
Wooldridge Source: From Salomon Brothers, Analytical Record of Yields and Yield Spreads, 1990. The folks at Salomon Brothers kindly provided the Record at no charge when I was an assistant professor at MIT. Data loads lazily.
data('intqrt')data('intqrt')
A data.frame with 124 observations on 23 variables:
r3: bond equiv. yield, 3 mo T-bill
r6: bond equiv. yield, 6 mo T-bill
r12: yield on 1 yr. bond
p3: price of 3 mo. T-bill
p6: price of 6 mo. T-bill
hy6: 100*(p3 - p6[_n-1])/p6[_n-1])
hy3: r3*(91/365)
spr63: r6 - r3
hy3_1: hy3[_n-1]
hy6_1: hy6[_n-1]
spr63_1: spr63[_n-1]
hy6hy3_1: hy6 - hy3_1
cr3: r3 - r3_1
r3_1: r3[_n-1]
chy6: hy6 - hy6_1
chy3: hy3 - hy3_1
chy6_1: chy6[_n-1]
chy3_1: chy3[_n-1]
cr6: r6 - r6_1
cr6_1: cr6[_n-1]
cr3_1: cr3[_n-1]
r6_1: r6[_n-1]
cspr63: spr63 - spr63_1
A nice feature of the Salomon Brothers data is that the interest rates are not averaged over a month or quarter – they are end-of-month or end-of-quarter rates. Asset pricing theories apply to such “point-sampled” data, and not to averages over a period. Most other sources report monthly or quarterly averages. This is a good data set to update and test whether current data are more or less supportive of basic asset pricing theories.
Used in Text: pages 405-406, 641, 646-647, 650, 652, 672, 673
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(intqrt)str(intqrt)
Wooldridge Source: Economic Report of the President, 1997, Tables B-4, B-20, B-61, and B-71. Data loads lazily.
data('inven')data('inven')
A data.frame with 37 observations on 13 variables:
year: 1959-1995
i3: 3 mo. T-bill rate
inf: CPI inflation rate
inven: inventories, billions '92 $
gdp: GDP, billions '92 $
r3: real interest: i3 - inf
cinven: inven - inven[_n-1]
cgdp: gdp - gdp[_n-1]
cr3: r3 - r3[_n-1]
ci3: i3 - i3[_n-1]
cinf: inf - inf[_n-1]
ginven: log(inven) - log(inven[_n-1])
ggdp: log(gdp) - log(gdp[_n-1])
pages 408, 444, 643, 830
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(inven)str(inven)
Wooldridge Source: H. Holzer, R. Block, M. Cheatham, and J. Knott (1993), “Are Training Subsidies Effective? The Michigan Experience,” Industrial and Labor Relations Review 46, 625-636. The authors kindly provided the data. Data loads lazily.
data('jtrain')data('jtrain')
A data.frame with 471 observations on 30 variables:
year: 1987, 1988, or 1989
fcode: firm code number
employ: # employees at plant
sales: annual sales, $
avgsal: average employee salary
scrap: scrap rate (per 100 items)
rework: rework rate (per 100 items)
tothrs: total hours training
union: =1 if unionized
grant: = 1 if received grant
d89: = 1 if year = 1989
d88: = 1 if year = 1988
totrain: total employees trained
hrsemp: tothrs/totrain
lscrap: log(scrap)
lemploy: log(employ)
lsales: log(sales)
lrework: log(rework)
lhrsemp: log(1 + hrsemp)
lscrap_1: lagged lscrap; missing 1987
grant_1: lagged grant; assumed 0 in 1987
clscrap: lscrap - lscrap_1; year > 1987
cgrant: grant - grant_1
clemploy: lemploy - lemploy[_n-1]
clsales: lavgsal - lavgsal[_n-1]
lavgsal: log(avgsal)
clavgsal: lavgsal - lavgsal[_n-1]
cgrant_1: cgrant[_n-1]
chrsemp: hrsemp - hrsemp[_n-1]
clhrsemp: lhrsemp - lhrsemp[_n-1]
pages 137, 161, 233, 254, 339, 465-466, 479, 486-487, 492, 504, 541-542, 774-775, 786-787, 788, 819.
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(jtrain)str(jtrain)
Wooldridge Source: R.J. Lalonde (1986), “Evaluating the Econometric Evaluations of Training Programs with Experimental Data,” American Economic Review 76, 604-620. Professor Jeff Biddle, at MSU, kindly passed the data set along to me. He obtained it from Professor Lalonde. Data loads lazily.
data('jtrain2')data('jtrain2')
A data.frame with 445 observations on 19 variables:
train: =1 if assigned to job training
age: age in 1977
educ: years of education
black: =1 if black
hisp: =1 if Hispanic
married: =1 if married
nodegree: =1 if no high school degree
mosinex: # mnths prior to 1/78 in expmnt
re74: real earns., 1974, $1000s
re75: real earns., 1975, $1000s
re78: real earns., 1978, $1000s
unem74: =1 if unem. all of 1974
unem75: =1 if unem. all of 1975
unem78: =1 if unem. all of 1978
lre74: log(re74); zero if re74 == 0
lre75: log(re75); zero if re75 == 0
lre78: log(re78); zero if re78 == 0
agesq: age^2
mostrn: months in training
Professor Lalonde obtained the data from the National Supported Work Demonstration job-training program conducted by the Manpower Demonstration Research Corporation in the mid 1970s. Training status was randomly assigned, so this is essentially experimental data. Computer Exercise C17.8 looks only at the effects of training on subsequent unemployment probabilities. For illustrating the more advanced methods in Chapter 17, a good exercise would be to have the students estimate a Tobit of re78 on train, and obtain estimates of the expected values for those with and without training. These can be compared with the sample averages.
Used in Text: pages 18, 340-341, 626
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(jtrain2)str(jtrain2)
Wooldridge Source: R.H. Dehejia and S. Wahba (1999), “Causal Effects in Nonexperimental Studies: Reevaluating the Evaluation of Training Programs,” Journal of the American Statistical Association 94, 1053-1062. Professor Sergio Firpo, at the University of British Columbia, has used this data set in his recent work, and he kindly provided it to me. This data set is a subset of that originally used by Lalonde in the study cited for JTRAIN2.RAW. Data loads lazily.
data('jtrain3')data('jtrain3')
A data.frame with 2675 observations on 20 variables:
train: =1 if in job training
age: in years, 1977
educ: years of schooling
black: =1 if black
hisp: =1 if Hispanic
married: =1 if married
re74: '74 earnings, $1000s '82
re75: '75 earnings, $1000s '82
unem75: =1 if unem. all of '75
unem74: =1 if unem. all of '74
re78: '78 earnings, $1000s '82
agesq: age^2
trre74: train*re74
trre75: train*re75
trun74: train*unem74
trun75: train*unem75
avgre: (re74 + re75)/2
travgre: train*avgre
unem78: =1 if unem. all of '78
em78: 1 - unem78
pages 340-341, 480-481
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(jtrain3)str(jtrain3)
Wooldridge Source: This is a data set I created many years ago intended as an update to the files JTRAIN2 and JTRAIN3. While the data were partly generated by me, the data attributes are similar to data sets used to evaluate job training programs. Data loads lazily.
data('jtrain98')data('jtrain98')
A data.frame with 1130 observations on 10 variables:
train: =1 if in job training
age: in years
educ: years of schooling
black: =1 if black
hisp: =1 if Hispanic
married: =1 if married
earn96: earnings in 1996, $1000s
unem96: =1 if unemployed all of 1995
earn98: earnings in 1998, $1000s
unem98: =1 if unemployed all of 1998
The response variables, earn98 and unem98, both have discreteness: the former is a corner solutions (takes on the value zero and then a range of strictly positive values) and the latter is binary. One could use these in an exercise using methods in Chapter 17. unem98 can be used in a probit or logit model, earn98 in a Tobit model, or in Poisson regression (without assuming, of course, that the Poisson distribution is correct).
Used in Text: 101-102, 248, 601
http://www.cengage.com/c/introductory-econometrics-a-modern-approach-7e-wooldridge
str(jtrain98)str(jtrain98)
Wooldridge Source: L.E. Papke (1995), “Participation in and Contributions to 401(k) Pension Plans:Evidence from Plan Data,” Journal of Human Resources 30, 311-325. Professor Papke kindly provided these data. She gathered them from the Internal Revenue Service’s Form 5500 tapes. Data loads lazily.
data('k401k')data('k401k')
A data.frame with 1534 observations on 8 variables:
prate: participation rate, percent
mrate: 401k plan match rate
totpart: total 401k participants
totelg: total eligible for 401k plan
age: age of 401k plan
totemp: total number of firm employees
sole: = 1 if 401k is firm's sole plan
ltotemp: log of totemp
This data set is used in a variety of ways in the text. One additional possibility is to investigate whether the coefficients from the regression of prate on mrate, log(totemp) differ by whether the plan is a sole plan. The Chow test (see Section 7.4), and the less restrictive version that allows different intercepts, can be used.
Used in Text: pages 63, 79, 136, 174, 219, 692
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(k401k)str(k401k)
Wooldridge Source: A. Abadie (2003), “Semiparametric Instrumental Variable Estimation of Treatment Response Models,” Journal of Econometrics 113, 231-263. Professor Abadie kindly provided these data. He obtained them from the 1991 Survey of Income and Program Participation (SIPP). Data loads lazily.
data('k401ksubs')data('k401ksubs')
A data.frame with 9275 observations on 11 variables:
e401k: =1 if eligble for 401(k)
inc: annual income, $1000s
marr: =1 if married
male: =1 if male respondent
age: in years
fsize: family size
nettfa: net total fin. assets, $1000
p401k: =1 if participate in 401(k)
pira: =1 if have IRA
incsq: inc^2
agesq: age^2
This data set can also be used to illustrate the binary response models, probit and logit, in Chapter 17, where, say, pira (an indicator for having an individual retirement account) is the dependent variable, and e401k [the 401(k) eligibility indicator] is the key explanatory variable.
Used in Text: pages 166, 174, 223, 264, 283, 301-302, 340, 549
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(k401ksubs)str(k401ksubs)
Wooldridge Source: K.A. Kiel and K.T. McClain (1995), “House Prices During Siting Decision Stages: The Case of an Incinerator from Rumor Through Operation,” Journal of Environmental Economics and Management 28, 241-255. Professor McClain kindly provided the data, of which I used only a subset. Data loads lazily.
data('kielmc')data('kielmc')
A data.frame with 321 observations on 25 variables:
year: 1978 or 1981
age: age of house
agesq: age^2
nbh: neighborhood, 1-6
cbd: dist. to cent. bus. dstrct, ft.
intst: dist. to interstate, ft.
lintst: log(intst)
price: selling price
rooms: # rooms in house
area: square footage of house
land: square footage lot
baths: # bathrooms
dist: dist. from house to incin., ft.
ldist: log(dist)
wind: prc. time wind incin. to house
lprice: log(price)
y81: =1 if year == 1981
larea: log(area)
lland: log(land)
y81ldist: y81*ldist
lintstsq: lintst^2
nearinc: =1 if dist <= 15840
y81nrinc: y81*nearinc
rprice: price, 1978 dollars
lrprice: log(rprice)
pages 220, 454-457, 475, 477
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(kielmc)str(kielmc)
Wooldridge Source: The subset of data for black or Hispanic women used in J.A. Angrist and W.E. Evans (1998) Data loads lazily.
data('labsup')data('labsup')
A data.frame with 31857 observations on 20 variables:
kids: number of kids
morekids: had more than 2 kids
boys2: first two births boys
girls2: first two births girls
boy1st: first birth boy
boy2nd: second birth boy
samesex: first two kids are of same sex
multi2nd: =1 if 2nd birth is twin
age: age of mom
agefstm: age of mom at first birth
black: =1 of black
hispan: =1 if hispanic
worked: mom worked last year
weeks: weeks worked mom
hours: hours of work per week, mom
labinc: mom's labor income, $1000s
faminc: family income, $1000s
nonmomi: 'non-mom' income, $1000s
educ: mom's years of education
agesq:
This example can promote an interesting discussion of instrument validity, and in particular, how a variable that is beyond our control – for example, whether the first two children have the same gender – can, nevertheless, affect subsequent economic choices. Students are asked to think about such issues in Computer Exercise C13 in Chapter 15. A more egregious version of this mistake would be to treat a variable such as age as a suitable instrument because it is beyond our control: clearly age has a direct effect on many economic outcomes that would play the role of the dependent variable.
Used in Text: pages 530-531
http://www.cengage.com/c/introductory-econometrics-a-modern-approach-7e-wooldridge
str(labsup)str(labsup)
Wooldridge Source: Collected by Kelly Barnett, an MSU economics student, for use in a term project. The data come from two sources: The Official Guide to U.S. Law Schools, 1986, Law School Admission Services, and The Gourman Report: A Ranking of Graduate and Professional Programs in American and International Universities, 1995, Washington, D.C. Data loads lazily.
data('lawsch85')data('lawsch85')
A data.frame with 156 observations on 21 variables:
rank: law school ranking
salary: median starting salary
cost: law school cost
LSAT: median LSAT score
GPA: median college GPA
libvol: no. volumes in lib., 1000s
faculty: no. of faculty
age: age of law sch., years
clsize: size of entering class
north: =1 if law sch in north
south: =1 if law sch in south
east: =1 if law sch in east
west: =1 if law sch in west
lsalary: log(salary)
studfac: student-faculty ratio
top10: =1 if ranked in top 10
r11_25: =1 if ranked 11-25
r26_40: =1 if ranked 26-40
r41_60: =1 if ranked 41-60
llibvol: log(libvol)
lcost: log(cost)
More recent versions of both cited documents are available. One could try a similar analysis for, say, MBA programs or Ph.D. programs in economics. Quality of placements may be a good dependent variable, and measures of business school or graduate program quality could be included among the explanatory variables. Of course, one would want to control for factors describing the incoming class so as to isolate the effect of the program itself.
Used in Text: pages 107, 164-165, 239
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(lawsch85)str(lawsch85)
Wooldridge Source: W.C. Hunter and M.B. Walker (1996), “The Cultural Affinity Hypothesis and Mortgage Lending Decisions,” Journal of Real Estate Finance and Economics 13, 57-70. Professor Walker kindly provided the data. Data loads lazily.
data('loanapp')data('loanapp')
A data.frame with 1989 observations on 59 variables:
occ: occupancy
loanamt: loan amt in thousands
action: type of action taken
msa: msa number of property
suffolk: =1 if property in suffolk co.
appinc: applicant income, $1000s
typur: type of purchaser of loan
unit: number of units in property
married: =1 if applicant married
dep: number of dependents
emp: years employed in line of work
yjob: years at this job
self: =1 if self employed
atotinc: total monthly income
cototinc: coapp total monthly income
hexp: propose housing expense
price: purchase price
other: other financing, $1000s
liq: liquid assets
rep: no. of credit reports
gdlin: credit history meets guidelines
lines: no. of credit lines on reports
mortg: credit history on mortgage paym
cons: credit history on consumer stuf
pubrec: =1 if filed bankruptcy
hrat: housing exp, percent total inc
obrat: other oblgs, percent total inc
fixadj: fixed or adjustable rate?
term: term of loan in months
apr: appraised value
prop: type of property
inss: PMI sought
inson: PMI approved
gift: gift as down payment
cosign: is there a cosigner
unver: unverifiable info
review: number of times reviewed
netw: net worth
unem: unemployment rate by industry
min30: =1 if minority pop. > 30percent
bd: =1 if boarded-up val > MSA med
mi: =1 if tract inc > MSA median
old: =1 if applic age > MSA median
vr: =1 if tract vac rte > MSA med
sch: =1 if > 12 years schooling
black: =1 if applicant black
hispan: =1 if applicant Hispanic
male: =1 if applicant male
reject: =1 if action == 3
approve: =1 if action == 1 or 2
mortno: no mortgage history
mortperf: no late mort. payments
mortlat1: one or two late payments
mortlat2: > 2 late payments
chist: =0 if accnts deliq. >= 60 days
multi: =1 if two or more units
loanprc: amt/price
thick: =1 if rep > 2
white: =1 if applicant white
These data were originally used in a famous study by researchers at the Boston Federal Reserve Bank. See A. Munnell, G.M.B. Tootell, L.E. Browne, and J. McEneaney (1996), “Mortgage Lending in Boston: Interpreting HMDA Data,” American Economic Review 86, 25-53.
Used in Text: pages 263-264, 300, 339-340, 624
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(loanapp)str(loanapp)
Wooldridge Source: Source: Statistical Abstract of the United States, 1990, 1993, and 1994. Data loads lazily.
data('lowbrth')data('lowbrth')
A data.frame with 100 observations on 36 variables:
year: 1987 or 1990
lowbrth: perc births low weight
infmort: infant mortality rate
afdcprt: # participants in AFDC, 1000s
popul: population, 1000s
pcinc: per capita income
physic: # physicians, 1000s
afdcprc: percent of pop in AFDC
d90: =1 if year == 1990
lpcinc: log of pcinc
cafdcprc: change in afdcprc
clpcinc: change in lpcinc
lphysic: log of physic
clphysic: change in lphysic
clowbrth: change in lowbrth
cinfmort: change in infmort
afdcpay: avg monthly AFDC payment
afdcinc: afdcpay as percent pcinc
lafdcpay: log of afdcpay
clafdcpy: change in lafdcpay
cafdcinc: change in afdcinc
stateabb: state postal code
state: name of state
beds: # hospital beds, 1000s
bedspc: beds per capita
lbedspc: log(bedspc)
clbedspc: change in lbedspc
povrate: percent people below poverty line
cpovrate: change in povrate
afdcpsq: afdcper^2
cafdcpsq: change in afdcpsq
physicpc: physicians per capita
lphypc: log(physicpc)
clphypc: change in lphypc
lpopul: log(popul)
clpopul: change in lpopul
This data set can be used very much like INFMRT.RAW. It contains two years of state-level panel data. In fact, it is a superset of INFMRT.RAW. The key is that it contains information on low birth weights, as well as infant mortality. It also contains state identifies, so that several years of more recent data could be added for a term project. Putting in the variable afcdprc and its square leads to some interesting findings for pooled OLS and fixed effects (first differencing). After differencing, you can even try using the change in the AFDC payments variable as an instrumental variable for the change in afdcprc.
Used in Text: not used
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(lowbrth)str(lowbrth)
Wooldridge Source: Leslie Papke, an economics professor at MSU, collected these data from Michigan Department of Education web site, www.michigan.gov/mde. These are district-level data, which Professor Papke kindly provided. She has used building-level data in “The Effects of Spending on Test Pass Rates: Evidence from Michigan” (2005), Journal of Public Economics 89, 821-839. Data loads lazily.
data('mathpnl')data('mathpnl')
A data.frame with 3850 observations on 52 variables:
distid: district identifier
intid: intermediate school district
lunch: percent eligible for free lunch
enrol: school enrollment
ptr: pupil/teacher: 1995-98
found: foundation grant, $: 1995-98
expp: expenditure per pupil
revpp: revenue per pupil
avgsal: average teacher salary
drop: high school dropout rate, percent
grad: high school grad. rate, percent
math4: percent satisfactory, 4th grade math
math7: percent satisfactory, 7th grade math
choice: number choice students
psa: # public school academy studs.
year: 1992-1998
staff: staff per 1000 students
avgben: avg teacher fringe benefits
y92: =1 if year == 1992
y93: =1 if year == 1993
y94: =1 if year == 1994
y95: =1 if year == 1995
y96: =1 if year == 1996
y97: =1 if year == 1997
y98: =1 if year == 1998
lexpp: log(expp)
lfound: log(found)
lexpp_1: lexpp[_n-1]
lfnd_1: lfnd[_n-1]
lenrol: log(enrol)
lenrolsq: lenrol^2
lunchsq: lunch^2
lfndsq: lfnd^2
math4_1: math4[_n-1]
cmath4: math4 - math4_1
gexpp: lexpp - lexpp_1
gexpp_1: gexpp[_n-1
gfound: lfound - lfnd_1
gfnd_1: gfound[_n-1]
clunch: lunch - lunch[_n-1]
clnchsq: lunchsq - lunchsq[_n-1]
genrol: lenrol - lenrol[_n-1]
genrolsq: genrol^2
expp92: expp in 1992
lexpp92: log(expp92)
math4_92: math4 in 1992
cpi: consumer price index
rexpp: real spending per pupil, 1997$
lrexpp: log(rexpp)
lrexpp_1: lrexpp[_n-1]
grexpp: lrexpp - lrexpp_1
grexpp_1: grexpp[_n-1]
pages 479-480, 505-506
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(mathpnl)str(mathpnl)
Wooldridge Source: Michigan Department of Education, www.michigan.gov/mde Data loads lazily.
data('meap00_01')data('meap00_01')
A data.frame with 1692 observations on 9 variables:
dcode: district code
bcode: building code
math4: percent students satisfactory, 4th grade math
read4: percent students satisfactory, 4th grade reading
lunch: percent students eligible for free or reduced lunch
enroll: school enrollment
exppp: expenditures per pupil: expend/enroll
lenroll: log(enroll)
lexppp: log(exppp)
pages 224, 302
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(meap00_01)str(meap00_01)
Wooldridge Source: Michigan Department of Education, www.michigan.gov/mde Data loads lazily.
data('meap01')data('meap01')
A data.frame with 1823 observations on 11 variables:
dcode: district code
bcode: building code
math4: percent students satisfactory, 4th grade math
read4: percent students satisfactory, 4th grade reading
lunch: percent students eligible for free or reduced lunch
enroll: school enrollment
expend: total spending, $
exppp: expenditures per pupil: expend/enroll
lenroll: log(enroll)
lexpend: log(expend)
lexppp: log(exppp)
This is another good data set to compare simple and multiple regression estimates. The expenditure variable (in logs, say) and the poverty measure (lunch) are negatively correlated in this data set. A simple regression of math4 on lexppp gives a negative coefficient. Controlling for lunch makes the spending coefficient positive and significant.
Used in Text: page 18
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(meap01)str(meap01)
Wooldridge Source: I collected these data from the old Michigan Department of Education web site. See MATHPNL.RAW for the current web site. I used data on most high schools in the state of Michigan for 1993. I dropped some high schools that had suspicious-looking data. Data loads lazily.
data('meap93')data('meap93')
A data.frame with 408 observations on 17 variables:
lnchprg: perc of studs in sch lnch prog
enroll: school enrollment
staff: staff per 1000 students
expend: expend. per stud, $
salary: avg. teacher salary, $
benefits: avg. teacher benefits, $
droprate: school dropout rate, perc
gradrate: school graduation rate, perc
math10: perc studs passing MEAP math
sci11: perc studs passing MEAP science
totcomp: salary + benefits
ltotcomp: log(totcomp)
lexpend: log of expend
lenroll: log(enroll)
lstaff: log(staff)
bensal: benefits/salary
lsalary: log(salary)
Many states have data, at either the district or building level, on student performance and spending. A good exercise in data collection and cleaning is to have students find such data for a particular state, and to put it into a form that can be used for econometric analysis.
Used in Text: pages 50, 65, 111-112, 127-128, 155-156, 219, 336, 339, 696-697
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(meap93)str(meap93)
Wooldridge Source: Collected by Professor Leslie Papke, an economics professor at MSU, from the Michigan Department of Education web site, www.michigan.gov/mde, and the U.S. Census Bureau. Professor Papke kindly provided the data. Data loads lazily.
data('meapsingle')data('meapsingle')
A data.frame with 229 observations on 18 variables:
dcode: district code
bcode: building code
math4: percent satisfactory, 4th grade math
read4: percent satisfactory, 4th grade reading
enroll: school enrollment
exppp: expenditures per pupil, $
free: percent eligible, free lunch
reduced: percent eligible, reduced lunch
lunch: free + reduced
medinc: zipcode median family, $ (1999)
totchild: # of children (in zipcode)
married: # of children in married-couple families
single: # of children not in married-couple families
pctsgle: percent of children not in married-couple families
zipcode: school zipcode
lenroll: log(enroll)
lexppp: log(exppp)
lmedinc: log(medinc)
100, 145-146, 198
http://www.cengage.com/c/introductory-econometrics-a-modern-approach-6e-wooldridge
str(meapsingle)str(meapsingle)
Wooldridge Source: P. Wolfson and D. Belman (2004), “The Minimum Wage: Consequences for Prices and Quantities in Low-Wage Labor Markets,” Journal of Business & Economic Statistics 22, 296-311. Professor Belman kindly provided the data. Data loads lazily.
data('minwage')data('minwage')
A data.frame with 612 observations on 58 variables:
emp232: employment, sector 232, 1000s
wage232: hourly wage, sector 232, $
emp236:
wage236:
emp234:
wage234:
emp314:
wage314:
emp228:
wage228:
emp233:
wage233:
emp394:
wage394:
emp231:
wage231:
emp226:
wage226:
emp387:
wage387:
emp056:
wage056:
unem: civilian unemployment rate, percent
cpi: Consumer Price Index (urban), 1982-1984 = 100
minwage: Federal minimum wage, $/hour
lemp232: log(emp232)
lwage232: log(wage232)
gemp232: lemp232 - lemp232[_n-1]
gwage232: lwage232 - lwage232[_n-1]
lminwage: log(minwage)
gmwage: lminwage - lminwage[_n-1]
gmwage_1: gmwage[_n-1]
gmwage_2:
gmwage_3:
gmwage_4:
gmwage_5:
gmwage_6:
gmwage_7:
gmwage_8:
gmwage_9:
gmwage_10:
gmwage_11:
gmwage_12:
lemp236:
gcpi: lcpi - lcpi[_n-1]
lcpi: log(cpi)
lwage236:
gemp236:
gwage236:
lemp234:
lwage234:
gemp234:
gwage234:
lemp314:
lwage314:
gemp314:
gwage314:
t: linear time trend, 1 to 612
The sectors corresponding to the different numbers in the data file are provided in the Wolfson and Bellman and article.
Used in Text: pages 379, 410, 444-445, 674-675
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(minwage)str(minwage)
Wooldridge Source: Collected by G. Mark Holmes, a former MSU undergraduate, for a term project. The salary data were obtained from the New York Times, April 11, 1993. The baseball statistics are from The Baseball Encyclopedia, 9th edition, and the city population figures are from the Statistical Abstract of the United States. Data loads lazily.
data('mlb1')data('mlb1')
A data.frame with 353 observations on 47 variables:
salary: 1993 season salary
teamsal: team payroll
nl: =1 if national league
years: years in major leagues
games: career games played
atbats: career at bats
runs: career runs scored
hits: career hits
doubles: career doubles
triples: career triples
hruns: career home runs
rbis: career runs batted in
bavg: career batting average
bb: career walks
so: career strike outs
sbases: career stolen bases
fldperc: career fielding perc
frstbase: = 1 if first base
scndbase: =1 if second base
shrtstop: =1 if shortstop
thrdbase: =1 if third base
outfield: =1 if outfield
catcher: =1 if catcher
yrsallst: years as all-star
hispan: =1 if hispanic
black: =1 if black
whitepop: white pop. in city
blackpop: black pop. in city
hisppop: hispanic pop. in city
pcinc: city per capita income
gamesyr: games per year in league
hrunsyr: home runs per year
atbatsyr: at bats per year
allstar: perc. of years an all-star
slugavg: career slugging average
rbisyr: rbis per year
sbasesyr: stolen bases per year
runsyr: runs scored per year
percwhte: percent white in city
percblck: percent black in city
perchisp: percent hispanic in city
blckpb: black*percblck
hispph: hispan*perchisp
whtepw: white*percwhte
blckph: black*perchisp
hisppb: hispan*percblck
lsalary: log(salary)
The baseball statistics are career statistics through the 1992 season. Players whose race or ethnicity could not be easily determined were not included. It should not be too difficult to obtain the city population and racial composition numbers for Montreal and Toronto for 1993. Of course, the data can be pretty easily obtained for more recent players.
Used in Text: pages 143-149, 165, 244-245, 262
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(mlb1)str(mlb1)
Wooldridge Source: T.A. Mroz (1987), “The Sensitivity of an Empirical Model of Married Women’s Hours of Work to Economic and Statistical Assumptions,” Econometrica 55, 765-799. Professor Ernst R. Berndt, of MIT, kindly provided the data, which he obtained from Professor Mroz. Data loads lazily.
data('mroz')data('mroz')
A data.frame with 753 observations on 22 variables:
inlf: =1 if in lab frce, 1975
hours: hours worked, 1975
kidslt6: # kids < 6 years
kidsge6: # kids 6-18
age: woman's age in yrs
educ: years of schooling
wage: est. wage from earn, hrs
repwage: rep. wage at interview in 1976
hushrs: hours worked by husband, 1975
husage: husband's age
huseduc: husband's years of schooling
huswage: husband's hourly wage, 1975
faminc: family income, 1975
mtr: fed. marg. tax rte facing woman
motheduc: mother's years of schooling
fatheduc: father's years of schooling
unem: unem. rate in county of resid.
city: =1 if live in SMSA
exper: actual labor mkt exper
nwifeinc: (faminc - wage*hours)/1000
lwage: log(wage)
expersq: exper^2
pages 249-251, 260, 294, 519-520, 530, 535, 535-536, 565-566, 578-579, 593- 595, 601-603, 619-620, 625
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(mroz)str(mroz)
Wooldridge Source: From the Statistical Abstract of the United States, 1995 (Tables 310 and 357), 1992 (Table 289). The execution data originally come from the U.S. Bureau of Justice Statistics, Capital Punishment Annual. Data loads lazily.
data('murder')data('murder')
A data.frame with 153 observations on 13 variables:
id: state identifier
state: postal code
year: 87, 90, or 93
mrdrte: murders per 100,000 people
exec: total executions, past 3 years
unem: annual unem. rate
d90: =1 if year == 90
d93: =1 if year == 93
cmrdrte: mrdrte - mrdrte[_n-1]
cexec: exec - exec[_n-1]
cunem: unem - unem[_n-1]
cexec_1: cexec[_n-1]
cunem_1: cunem[_n-1]
Prosecutors in different counties might pursue the death penalty with different intensities, so it makes sense to collect murder and execution data at the county level. This could be combined with better demographic information at the county level, along with better economic data (say, on wages for various kinds of employment).
Used in Text: pages 480, 505, 548
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(murder)str(murder)
Wooldridge Source: Collected by Christopher Torrente, a former MSU undergraduate, for a term project. He obtained the salary data and the career statistics from The Complete Handbook of Pro Basketball, 1995, edited by Zander Hollander. New York: Signet. The demographic information (marital status, number of children, and so on) was obtained from the teams’ 1994-1995 media guides. Data loads lazily.
data('nbasal')data('nbasal')
A data.frame with 269 observations on 22 variables:
marr: =1 if married
wage: annual salary, thousands $
exper: years as professional player
age: age in years
coll: years played in college
games: average games per year
minutes: average minutes per year
guard: =1 if guard
forward: =1 if forward
center: =1 if center
points: points per game
rebounds: rebounds per game
assists: assists per game
draft: draft number
allstar: =1 if ever all star
avgmin: minutes per game
lwage: log(wage)
black: =1 if black
children: =1 if has children
expersq: exper^2
agesq: age^2
marrblck: marr*black
A panel version of this data set could be useful for further isolating productivity effects of marital status. One would need to obtain information on enough different players in at least two years, where some players who were not married in the initial year are married in later years. Fixed effects (or first differencing, for two years) is the natural estimation method.
Used in Text: pages 222-223, 264-265
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(nbasal)str(nbasal)
Wooldridge Source: Data on NCAA men’s basketball teams, collected by Weizhao Sun for a senior seminar project in sports economics at Michigan State University, Spring 2017. He used various sources, including www.espn.com and www.teamrankings.com/ncaa-basketball/rpi-ranking/rpi-rating-by-team. Data loads lazily.
data('ncaa_rpi')data('ncaa_rpi')
A data.frame with 336 observations on 14 variables:
team: Name
year: Year
conference: Conference
postrpi: Post Rank
prerpi: Preseason Rank
postrpi_1: Post Rank 1 yr ago
postrpi_2: Post Rank 2 yrs ago
recruitrank: Recruits Rank
wins: Number of games won
losses: Number of games lost
winperc: Winning Percentage
tourney: Tournament dummy
coachexper: Coach Experience
power5: PowerFive Dummy
This is a nice example of how multiple regression analysis can be used to determine whether rankings compiled by experts – the so-called pre-season RPI in this case – provide additional information beyond what we can obtain from widely available data bases. A simple and interesting question is whether, once the previous year’s post-season RPI is controlled for, does the pre-season RPI – which is supposed to add information on recruiting and player development – help to predict performance (such as win percentage or making it to the NCAA men’s basketball tournament). For the binary outcome that indicates making it to the NCAA tournament, a probit or logit model can be used for courses that introduce more advanced methods. There are some other interesting variables, such as coaching experience, that can be included, too.
Used in Text: not used
http://www.cengage.com/c/introductory-econometrics-a-modern-approach-7e-wooldridge
str(ncaa_rpi)str(ncaa_rpi)
Wooldridge Source: These are Wednesday closing prices of value-weighted NYSE average, available in many publications. I do not recall the particular source I used when I collected these data at MIT. Probably the easiest way to get similar data is to go to the NYSE web site, www.nyse.com. Data loads lazily.
data('nyse')data('nyse')
A data.frame with 691 observations on 8 variables:
price: NYSE stock price index
return: 100*(p - p(-1))/p(-1))
return_1: lagged return
t:
price_1:
price_2:
cprice: price - price_1
cprice_1: lagged cprice
pages 388-389, 407, 436, 438, 440-441, 442, 663-664
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(nyse)str(nyse)
Wooldridge Source: Economic Report of the President, 2007, Tables B-4 and B-42. Data loads lazily.
data('okun')data('okun')
A data.frame with 47 observations on 4 variables:
year: 1959 through 2005
pcrgdp: percentage change in real GDP
unem: civilian unemployment rate
cunem: unem - unem[_n-1]
410, 444
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(okun)str(okun)
Wooldridge Source: D. Romer (1993), “Openness and Inflation: Theory and Evidence,” Quarterly Journal of Economics 108, 869-903. The data are included in the article. Data loads lazily.
data('openness')data('openness')
A data.frame with 114 observations on 12 variables:
open: imports as percent GDP, '73-
inf: avg. annual inflation, '73-
pcinc: 1980 per capita inc., U.S. $
land: land area, square miles
oil: =1 if major oil producer
good: =1 if 'good' data
lpcinc: log(pcinc)
lland: log(land)
lopen: log(open)
linf: log(inf)
opendec: open/100
linfdec: log(inf/100)
pages 566, 579
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(openness)str(openness)
Wooldridge Source: L.E. Papke (2004), “Individual Financial Decisions in Retirement Saving: The Role of Participant-Direction,” Journal of Public Economics 88, 39-61. Professor Papke kindly provided the data. She collected them from the National Longitudinal Survey of Mature Women, 1991. Data loads lazily.
data('pension')data('pension')
A data.frame with 194 observations on 19 variables:
id: family identifier
pyears: years in pension plan
prftshr: =1 if profit sharing plan
choice: =1 if can choose method invest
female: =1 if female
married: =1 if married
age: age in years
educ: highest grade completed
finc25: $15,000 < faminc92 <= $25,000
finc35: $25,000 < faminc92 <= $35,000
finc50: $35,000 < faminc92 <= $50,000
finc75: $50,000 < faminc92 <= $75,000
finc100: $75,000 < faminc92 <= $100,000
finc101: $100,000 < faminc92
wealth89: net worth, 1989, $1000
black: =1 if black
stckin89: =1 if owned stock in 1989
irain89: =1 if had IRA in 1989
pctstck: 0=mstbnds,50=mixed,100=mststcks
page 506
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(pension)str(pension)
Wooldridge Source: Economic Report of the President, 2004, Tables B-42 and B-64. Data loads lazily.
data('phillips')data('phillips')
A data.frame with 56 observations on 7 variables:
year: 1948 through 2003
unem: civilian unemployment rate, percent
inf: percentage change in CPI
inf_1: inf[_n-1]
unem_1: unem[_n-1]
cinf: inf - inf_1
cunem: unem - unem_1
pages 355-356, 379, 390-391, 408, 409, 409, 418, 428, 443, 548-549, 642, 656, 659, 662, 672, 817.
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(phillips)str(phillips)
Wooldridge Source: Collected by Scott Resnick, a former MSU undergraduate, from various newspaper sources. Data loads lazily.
data('pntsprd')data('pntsprd')
A data.frame with 553 observations on 12 variables:
favscr: favored team's score
undscr: underdog's score
spread: las vegas spread
favhome: =1 if favored team at home
neutral: =1 if neutral site
fav25: =1 if favored team in top 25
und25: =1 if underdog in top 25
fregion: favorite's region of country
uregion: underdog's region of country
scrdiff: favscr - undscr
sprdcvr: =1 if spread covered
favwin: =1 if favored team wins
The data are for the 1994-1995 men’s college basketball seasons. The spread is for the day before the game was played. One might collect more recent data and determine whether the spread has become a less accurate predictor of the actual outcome in more recent years. In other words, in the simple regression of the actual score differential on the spread, is the variance larger in more recent years. (We should fully expect the slope coefficient not to be statistically different from one.)
Used in Text: pages 300, 624, 697
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(pntsprd)str(pntsprd)
Wooldridge Source: S.D. Levitt (1996), “The Effect of Prison Population Size on Crime Rates: Evidence from Prison Overcrowding Legislation,” Quarterly Journal of Economics 111, 319-351. Professor Levitt kindly provided me with the data, of which I used a subset. Data loads lazily.
data('prison')data('prison')
A data.frame with 714 observations on 45 variables:
state: alphabetical; DC = 9
year: 80 to 93
govelec: =1 if gubernatorial election
black: proportion black
metro: proportion in metro. areas
unem: proportion unemployed
criv: viol. crimes per 100,000
crip: prop. crimes per 100,000
lcriv: log(criv)
lcrip: log(crip)
gcriv: lcriv - lcriv_1
gcrip: lcrip - lcrip_1
y81: =1 if year == 81
y82:
y83:
y84:
y85:
y86:
y87:
y88:
y89:
y90:
y91:
y92:
y93:
ag0_14: prop. pop. 0 to 14 yrs
ag15_17: prop. pop. 15 to 17 yrs
ag18_24: prop. pop. 18 to 24 yrs
ag25_34: prop. pop. 25 to 34 yrs
incpc: per capita income, nominal
polpc: police per 100,000 residents
gincpc: log(incpc) - log(incpc_1)
gpolpc: lpolpc - lpolpc_1
cag0_14: change in ag0_14
cag15_17: change in ag15_17
cag18_24: change in ag18_24
cag25_34: change in ag25_34
cunem: change in unem
cblack: change in black
cmetro: change in metro
pris: prison pop. per 100,000
lpris: log(pris)
gpris: lpris - lpris[_n-1]
final1: =1 if fnl dec on litig, curr yr
final2: =1 if dec on litig, prev 2 yrs
pages 573-574
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(prison)str(prison)
Wooldridge Source: A.J. Castillo-Freeman and R.B. Freeman (1992), “When the Minimum Wage Really Bites: The Effect of the U.S.-Level Minimum Wage on Puerto Rico,” in Immigration and the Work Force, edited by G.J. Borjas and R.B. Freeman, 177-211. Chicago: University of Chicago Press. The data are reported in the article. Data loads lazily.
data('prminwge')data('prminwge')
A data.frame with 38 observations on 25 variables:
year: 1950-1987
avgmin: weighted avg min wge, 44 indust
avgwage: wghted avg hrly wge, 44 indust
kaitz: Kaitz min wage index
avgcov: wghted avg coverage, 8 indust
covt: economy-wide coverage of min wg
mfgwage: avg manuf. wage
prdef: Puerto Rican price deflator
prepop: PR employ/popul ratio
prepopf: PR employ/popul ratio, alter.
prgnp: PR GNP
prunemp: PR unemployment rate
usgnp: US GNP
t: time trend: 1 to 38
post74: time trend: starts in 1974
lprunemp: log(prunemp)
lprgnp: log(prgnp)
lusgnp: log(usgnp)
lkaitz: log(kaitz)
lprun_1: lprunemp[_n-1]
lprepop: log(prepop)
lprep_1: lprepop[_n-1]
mincov: (avgmin/avgwage)*avgcov
lmincov: log(mincov)
lavgmin: log(avgmin)
Given the ongoing debate on the employment effects of the minimum wage, this would be a great data set to try to update. The coverage rates are the most difficult variables to construct.
Used in Text: pages 356-357, 369-370, 420-421, 434
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(prminwge)str(prminwge)
Wooldridge Source: From Businessweek R&D Scoreboard, October 25, 1991. Data loads lazily.
data('rdchem')data('rdchem')
A data.frame with 32 observations on 8 variables:
rd: R&D spending, millions
sales: firm sales, millions
profits: profits, millions
rdintens: rd as percent of sales
profmarg: profits as percent of sales
salessq: sales^2
lsales: log(sales)
lrd: log(rd)
It would be interesting to collect more recent data and see whether the R&D/firm size relationship has changed over time.
Used in Text: pages 64, 139-140, 159-160, 204, 218, 327-329, 339
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(rdchem)str(rdchem)
Wooldridge Source: See RDCHEM.RAW Data loads lazily.
data('rdtelec')data('rdtelec')
A data.frame with 29 observations on 6 variables:
rd: R&D spending, millions $
sales: firm sales, millions $
rdintens: rd as percent of sales
lrd: log(rd)
lsales: log(sales)
salessq: sales^2
According to these data, the R&D/firm size relationship is different in the telecommunications industry than in the chemical industry: there is pretty strong evidence that R&D intensity decreases with firm size in telecommunications. Of course, that was in 1991. The data could easily be updated, and a panel data set could be constructed.
Used in Text: not used
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(rdtelec)str(rdtelec)
Wooldridge Source: C.-F. Chung, P. Schmidt, and A.D. Witte (1991), “Survival Analysis: A Survey,” Journal of Quantitative Criminology 7, 59-98. Professor Chung kindly provided the data. Data loads lazily.
data('recid')data('recid')
A data.frame with 1445 observations on 18 variables:
black: =1 if black
alcohol: =1 if alcohol problems
drugs: =1 if drug history
super: =1 if release supervised
married: =1 if married when incarc.
felon: =1 if felony sentence
workprg: =1 if in N.C. pris. work prg.
property: =1 if property crime
person: =1 if crime against person
priors: # prior convictions
educ: years of schooling
rules: # rules violations in prison
age: in months
tserved: time served, rounded to months
follow: length follow period, months
durat: min(time until return, follow)
cens: =1 if duration right censored
ldurat: log(durat)
pages 611-612, 625
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(recid)str(recid)
Wooldridge Source: David Harvey, a former MSU undergraduate, collected the data for 64 “college towns” from the 1980 and 1990 United States censuses. Data loads lazily.
data('rental')data('rental')
A data.frame with 128 observations on 23 variables:
city: city label, 1 to 64
year: 80 or 90
pop: city population
enroll: # college students enrolled
rent: average rent
rnthsg: renter occupied units
tothsg: occupied housing units
avginc: per capita income
lenroll: log(enroll)
lpop: log(pop)
lrent: log(rent)
ltothsg: log(tothsg)
lrnthsg: log(rnthsg)
lavginc: log(avginc)
clenroll: change in lrent from 80 to 90
clpop: change in lpop
clrent: change in lrent
cltothsg: change in ltothsg
clrnthsg: change in lrnthsg
clavginc: change in lavginc
pctstu: percent of population students
cpctstu: change in pctstu
y90: =1 if year == 90
These data can be used in a somewhat crude simultaneous equations analysis, either focusing on one year or pooling the two years. (In the latter case, in an advanced class, you might have students compute the standard errors robust to serial correlation across the two time periods.) The demand equation would have ltothsg as a function of lrent, lavginc, and lpop. The supply equation would have ltothsg as a function of lrent, pctst, and lpop. Thus, in estimating the demand function, pctstu is used as an IV for lrent. Clearly one can quibble with excluding pctstu from the demand equation, but the estimated demand function gives a negative price effect. Getting information for 2000, and adding many more college towns, would make for a much better analysis. Information on number of spaces in on-campus dormitories would be a big improvement, too.
Used in Text: pages 160, 477, 503-504
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(rental)str(rental)
Wooldridge Source: Collected by Stephanie Balys, a former MSU undergraduate, from the New York Stock Exchange and Compustat. Data loads lazily.
data('return')data('return')
A data.frame with 142 observations on 12 variables:
roe: return on equity, 1990
rok: return on capital, 1990
dkr: debt/capital, 1990
eps: earnings per share, 1990
netinc: net income, 1990 (mills.)
sp90: stock price, end 1990
sp94: stock price, end 1994
salary: CEO salary, 1990 (thous.)
return: percent change s.p., 90-94
lsalary: log(salary)
lsp90: log(sp90)
lnetinc: log(netinc)
More can be done with this data set. Recently, I discovered that lsp90 does appear to predict return (and the log of the 1990 stock price works better than sp90). I am a little suspicious, but you could use the negative coefficient on lsp90 to illustrate “reversion to the mean.”
Used in Text: page 162-163
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(return)str(return)
Wooldridge Source: Unknown Data loads lazily.
data('saving')data('saving')
A data.frame with 100 observations on 7 variables:
sav: annual savings, $
inc: annual income, $
size: family size
educ: years educ, household head
age: age of household head
black: =1 if household head is black
cons: annual consumption, $
I remember entering this data set in the late 1980s, and I am pretty sure it came directly from an introductory econometrics text. But so far my search has been fruitless. If anyone runs across this data set, I would appreciate knowing about it.
Used in Text: not used
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(saving)str(saving)
Wooldridge Source: L.E. Papke (2005), “The Effects of Spending on Test Pass Rates: Evidence from Michigan,” Journal of Public Economics 89, 821-839. Data loads lazily.
data('school93_98')data('school93_98')
A data.frame with 10668 observations on 18 variables:
distid:
schid:
lunch: percent eligible for free lunch
enrol: number of students
exppp: exp per pupil
math4:
year: 1993 = school year 1992-1993
y93:
y94:
y95:
y96:
y97:
y98:
rexpp: (exppp/cpi)1.605: 1997 $
found:
lenrol: log(enrol)
lrexpp: log(rexpp)
lavgrexpp: log((rexpp + L.rexpp)/2)
This is closer to the data actually used in the Papke paper as it is at the school (building) level. It is unbalanced because data on scores and some of the spending and other variables is missing for some schools. While the usual RE and FE methods can be applied directly, obtaining the correlated random effects version of the Hausman test is more advance. Computer Exercise 17 in Chapter 14 walks the reader through it.
Used in Text: page 491
http://www.cengage.com/c/introductory-econometrics-a-modern-approach-7e-wooldridge
str(school93_98)str(school93_98)
Wooldridge Source: J.E. Biddle and D.S. Hamermesh (1990), “Sleep and the Allocation of Time,” Journal of Political Economy 98, 922-943. Professor Biddle kindly provided the data. Data loads lazily.
data('sleep75')data('sleep75')
A data.frame with 706 observations on 34 variables:
age: in years
black: =1 if black
case: identifier
clerical: =1 if clerical worker
construc: =1 if construction worker
educ: years of schooling
earns74: total earnings, 1974
gdhlth: =1 if in good or excel. health
inlf: =1 if in labor force
leis1: sleep - totwrk
leis2: slpnaps - totwrk
leis3: rlxall - totwrk
smsa: =1 if live in smsa
lhrwage: log hourly wage
lothinc: log othinc, unless othinc < 0
male: =1 if male
marr: =1 if married
prot: =1 if Protestant
rlxall: slpnaps + personal activs
selfe: =1 if self employed
sleep: mins sleep at night, per wk
slpnaps: minutes sleep, inc. naps
south: =1 if live in south
spsepay: spousal wage income
spwrk75: =1 if spouse works
totwrk: mins worked per week
union: =1 if belong to union
worknrm: mins work main job
workscnd: mins work second job
exper: age - educ - 6
yngkid: =1 if children < 3 present
yrsmarr: years married
hrwage: hourly wage
agesq: age^2
In their article, Biddle and Hamermesh include an hourly wage measure in the sleep equation. An econometric problem that arises is that the hourly wage is missing for those who do not work. Plus, the wage offer may be endogenous (even if it were always observed). Biddle and Hamermesh employ extensions of the sample selection methods in Section 17.5. See their article for details.
Used in Text: pages 64, 106-107, 162, 259, 263, 299
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(sleep75)str(sleep75)
Wooldridge Source: See SLEEP75.RAW Data loads lazily.
data('slp75_81')data('slp75_81')
A data.frame with 239 observations on 20 variables:
age75: age in 1975
educ75: years educ in '75
educ81: years educ in '81
gdhlth75: = 1 if good hlth in '75
gdhlth81: =1 if good hlth in '81
male: =1 if male
marr75: = 1 if married in '75
marr81: =1 if married in '81
slpnap75: mins slp wk, inc naps, '75
slpnap81: mins slp wk, inc naps, '81
totwrk75: minutes worked per week, '75
totwrk81: minutes worked per week, '81
yngkid75: = 1 if child < 3, '75
yngkid81: =1 if child < 3, '81
ceduc: change in educ
cgdhlth: change in gdhlth
cmarr: change in marr
cslpnap: change in slpnap
ctotwrk: change in totwrk
cyngkid: change in yngkid
pages 463-464
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(slp75_81)str(slp75_81)
Wooldridge Source: J. Mullahy (1997), “Instrumental-Variable Estimation of Count Data Models: Applications to Models of Cigarette Smoking Behavior,” Review of Economics and Statistics 79, 596-593. Professor Mullahy kindly provided the data. Data loads lazily.
data('smoke')data('smoke')
A data.frame with 807 observations on 10 variables:
educ: years of schooling
cigpric: state cig. price, cents/pack
white: =1 if white
age: in years
income: annual income, $
cigs: cigs. smoked per day
restaurn: =1 if rest. smk. restrictions
lincome: log(income)
agesq: age^2
lcigpric: log(cigprice)
If you want to do a “fancy” IV version of Computer Exercise C16.1, you could estimate a reduced form count model for cigs using the Poisson regression methods in Section 17.3, and then use the fitted values as an IV for cigs. Presumably, this would be for a fairly advanced class.
Used in Text: pages 183, 288-289, 298, 301, 578, 627
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(smoke)str(smoke)
Wooldridge Source: I collected these data from two sources, the 1992 Statistical Abstract of the United States (Tables 1009, 1012) and A Digest of State Alcohol-Highway Safety Related Legislation, 1985 and 1990, published by the U.S. National Highway Traffic Safety Administration. Data loads lazily.
data('traffic1')data('traffic1')
A data.frame with 51 observations on 13 variables:
state:
admn90: =1 if admin. revoc., '90
admn85: =1 if admin. revoc., '85
open90: =1 if open cont. law, '90
open85: =1 if open cont. law, '85
dthrte90: deaths per 100 mill. miles, '90
dthrte85: deaths per 100 mill. miles, '85
speed90: =1 if 65 mph, 1990
speed85: =0 always
cdthrte: dthrte90 - dthrte85
cadmn: admn90 - admn85
copen: open90 - open85
cspeed: speed90 - speed85
In addition to adding recent years, this data set could really use state-level tax rates on alcohol. Other important law changes include defining driving under the influence as having a blood alcohol level of .08 or more, which many states have adopted since the 1980s. The trend really picked up in the 1990s and continued through the 2000s.
Used in Text: pages 467-468, 688?
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(traffic1)str(traffic1)
Wooldridge Source: P.S. McCarthy (1994), “Relaxed Speed Limits and Highway Safety: New Evidence from California,” Economics Letters 46, 173-179. Professor McCarthy kindly provided the data. Data loads lazily.
data('traffic2')data('traffic2')
A data.frame with 108 observations on 48 variables:
year: 1981 to 1989
totacc: statewide total accidents
fatacc: statewide fatal accidents
injacc: statewide injury accidents
pdoacc: property damage only accidents
ntotacc: noninterstate total acc.
nfatacc: noninterstate fatal acc.
ninjacc: noninterstate injur acc.
npdoacc: noninterstate property acc.
rtotacc: tot. acc. on rural 65 mph roads
rfatacc: fat. acc. on rural 65 mph roads
rinjacc: inj. acc. on rural 65 mph roads
rpdoacc: prp. acc. on rural 65 mph roads
ushigh: acc. on U.S. highways
cntyrds: acc. on county roads
strtes: acc. on state routes
t: time trend
tsq: t^2
unem: state unemployment rate
spdlaw: =1 after 65 mph in effect
beltlaw: =1 after seatbelt law
wkends: # weekends in month
feb: =1 if month is Feb.
mar:
apr:
may:
jun:
jul:
aug:
sep:
oct:
nov:
dec:
ltotacc: log(totacc)
lfatacc: log(fatacc)
prcfat: 100*(fatacc/totacc)
prcrfat: 100*(rfatacc/rtotacc)
lrtotacc: log(rtotacc)
lrfatacc: log(rfatacc)
lntotacc: log(ntotacc)
lnfatacc: log(nfatacc)
prcnfat: 100*(nfatacc/ntotacc)
lushigh: log(ushigh)
lcntyrds: log(cntyrds)
lstrtes: log(strtes)
spdt: spdlaw*t
beltt: beltlaw*t
prcfat_1: prcfat[_n-1]
Many states have changed maximum speed limits and imposed seat belt laws over the past 25 years. Data similar to those in TRAFFIC2.RAW should be fairly easy to obtain for a particular state. One should combine this information with changes in a state’s blood alcohol limit and the passage of per se and open container laws.
Used in Text: pages 378-379, 409, 443, 674, 695-696
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(traffic2)str(traffic2)
Wooldridge Source: T.J. Kane and C.E. Rouse (1995), Labor-Market Returns to Two- and Four-Year Colleges, American Economic Review 85, 600-614. With Professor Rouse’s kind assistance, I obtained the data from her web site at Princeton University. Data loads lazily.
data('twoyear')data('twoyear')
A data.frame with 6763 observations on 23 variables:
female: =1 if female
phsrank: percent high school rank; 100 = best
BA: =1 if Bachelor's degree
AA: =1 if Associate's degree
black: =1 if African-American
hispanic: =1 if Hispanic
id: ID Number
exper: total (actual) work experience
jc: total 2-year credits
univ: total 4-year credits
lwage: log hourly wage
stotal: total standardized test score
smcity: =1 if small city, 1972
medcity: =1 if med. city, 1972
submed: =1 if suburb med. city, 1972
lgcity: =1 if large city, 1972
sublg: =1 if suburb large city, 1972
vlgcity: =1 if very large city, 1972
subvlg: =1 if sub. very lge. city, 1972
ne: =1 if northeast
nc: =1 if north central
south: =1 if south
totcoll: jc + univ
As possible extensions, students can explore whether the returns to two-year or four-year colleges depend on race or gender. This is partly done in Problem 7.9 but where college is aggregated into one number. Also, should experience appear as a quadratic in the wage specification?
Used in Text: pages 140-143, 165, 261, 340
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(twoyear)str(twoyear)
Wooldridge Source: J.D. Hamilton and L. Gang (1996), “Stock Market Volatility and the Business Cycle,” Journal of Applied Econometrics 11, 573-593. I obtained these data from the Journal of Applied Econometrics data archive at http://qed.econ.queensu.ca/jae/ Data loads lazily.
data('volat')data('volat')
A data.frame with 558 observations on 17 variables:
date: 1947.01 to 1993.06
sp500: S&P 500 index
divyld: div. yield annualized rate
i3: 3 mo. T-bill annualized rate
ip: index of industrial production
pcsp: pct chg, sp500, ann rate
rsp500: return on sp500: pcsp + divyld
pcip: pct chg, IP, ann rate
ci3: i3 - i3[_n-1]
ci3_1: ci3[_n-1]
ci3_2: ci3[_n-2]
pcip_1: pcip[_n-1]
pcip_2: pcip[_n-2]
pcip_3: pcip[_n-3]
pcsp_1: pcip[_n-1]
pcsp_2: pcip[_n-2]
pcsp_3: pcip[_n-3]
pages 378, 670, 671, 674
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(volat)str(volat)
Wooldridge Source: From M. Barone and G. Ujifusa, The Almanac of American Politics, 1992. Washington, DC: National Journal. Data loads lazily.
data('vote1')data('vote1')
A data.frame with 173 observations on 10 variables:
state: state postal code
district: congressional district
democA: =1 if A is democrat
voteA: percent vote for A
expendA: camp. expends. by A, $1000s
expendB: camp. expends. by B, $1000s
prtystrA: percent vote for president
lexpendA: log(expendA)
lexpendB: log(expendB)
shareA: 100*(expendA/(expendA+expendB))
pages 34, 39, 164, 221-222, 299, 699
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(vote1)str(vote1)
Wooldridge Source: See VOTE1.RAW Data loads lazily.
data('vote2')data('vote2')
A data.frame with 186 observations on 26 variables:
state: state postal code
district: U.S. Congressional district
democ: =1 if incumbent democrat
vote90: inc. share two-party vote, 1990
vote88: inc. share two-party vote, 1988
inexp90: inc. camp. expends., 1990
chexp90: chl. camp. expends., 1990
inexp88: inc. camp. expends., 1988
chexp88: chl. camp. expends., 1988
prtystr: percent vote pres., same party, 1988
rptchall: =1 if a repeat challenger
tenure: years in H.R.
lawyer: =1 if law degree
linexp90: log(inexp90)
lchexp90: log(chexp90)
linexp88: log(inexp88)
lchexp88: log(chexp88)
incshr90: 100*(inexp90/(inexp90+chexp90))
incshr88: 100*(inexp88/(inexp88+chexp88))
cvote: vote90 - vote88
clinexp: linexp90 - linexp88
clchexp: lchexp90 - lchexp88
cincshr: incshr90 - incshr88
win88: =1 by definition
win90: =1 if inc. wins, 1990
cwin: win90 - win88
These are panel data, at the Congressional district level, collected for the 1988 and 1990 U.S. House of Representative elections. Of course, much more recent data are available, possibly even in electronic form.
Used in Text: pages 335-336, 478, 699
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(vote2)str(vote2)
Wooldridge Source: Rouse, C.E. (1998), “Private School Vouchers and Student Achievement: An Evaluation of the Milwaukee Parental Choice Program,” Quarterly Journal of Economics 113, 553-602. Professor Rouse kindly provided the original data set from her paper. Data loads lazily.
data('voucher')data('voucher')
A data.frame with 990 observations on 19 variables:
studyid: student identifier
black: = 1 if African-American
hispanic: = 1 if Hispanic
female: = 1 if female
appyear: year of first application: 90 to 93
mnce: math NCE test score, 1994
select: = 1 if ever selected to attend choice school
choice: = 1 if attending choice school, 1994
selectyrs: years selected to attend choice school
choiceyrs: years attended choice school
mnce90: mnce in 1990
selectyrs1: = 1 if selectyrs == 1
selectyrs2: = 1 if selectyrs == 2
selectyrs3: = 1 if selectyrs == 3
selectyrs4: = 1 if selectyrs == 4
choiceyrs1: = 1 if choiceyrs == 1
choiceyrs2: = 1 if choiceyrs == 2
choiceyrs3: = 1 if choiceyrs == 3
choiceyrs4: = 1 if choiceyrs == 4
This is a condensed version of the data set used by Professor Rouse. The original data set had missing information on many variables, including post-policy and pre-policy test scores. I did not impute any missing data and have dropped observations that were unusable without filling in missing data. There are 990 students in the current data set but pre-policy test scores are available for only 328 of them. This is a good example of where eligibility for a program is randomized but participation need not be. In addition, even if we look at just the effect of eligibility (captured in the variable selectyrs) on the math test score (mnce), we need to confront the fact that attrition (students leaving the district) can bias the results. Controlling for the pre-policy test score, mnce90, can help – but at the cost of losing two-thirds of the observations. A simple regression of mnce on selectyrs followed by a multiple regression that adds mnce90 as a control is informative. The selectyrs dummy variables can be used as instrumental variables for the choiceyrs variable to try to estimate the effect of actually participating in the program (rather than estimating the so- called intention-to-treat effect). Computer Exercise C15.11 steps through the details.
Used in Text: pages 550-551
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(voucher)str(voucher)
Wooldridge Source: These are data from the 1976 Current Population Survey, collected by Henry Farber when he and I were colleagues at MIT in 1988. Data loads lazily.
data('wage1')data('wage1')
A data.frame with 526 observations on 24 variables:
wage: average hourly earnings
educ: years of education
exper: years potential experience
tenure: years with current employer
nonwhite: =1 if nonwhite
female: =1 if female
married: =1 if married
numdep: number of dependents
smsa: =1 if live in SMSA
northcen: =1 if live in north central U.S
south: =1 if live in southern region
west: =1 if live in western region
construc: =1 if work in construc. indus.
ndurman: =1 if in nondur. manuf. indus.
trcommpu: =1 if in trans, commun, pub ut
trade: =1 if in wholesale or retail
services: =1 if in services indus.
profserv: =1 if in prof. serv. indus.
profocc: =1 if in profess. occupation
clerocc: =1 if in clerical occupation
servocc: =1 if in service occupation
lwage: log(wage)
expersq: exper^2
tenursq: tenure^2
Barry Murphy, of the University of Portsmouth in the UK, has pointed out that for several observations the values for exper and tenure are in logical conflict. In particular, for some workers the number of years with current employer (tenure) is greater than overall work experience (exper). At least some of these conflicts are due to the definition of exper as “potential” work experience, but probably not all. Nevertheless, I am using the data set as it was supplied to me.
Used in Text: pages 7, 17, 33-34, 37, 76, 91, 125, 183, 194-195, 220, 231, 234, 235-236, 240-241, 243-244, 263, 272, 326, 678
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(wage1)str(wage1)
Wooldridge Source: M. Blackburn and D. Neumark (1992), “Unobserved Ability, Efficiency Wages, and Interindustry Wage Differentials,” Quarterly Journal of Economics 107, 1421-1436. Professor Neumark kindly provided the data, of which I used just the data for 1980. Data loads lazily.
data('wage2')data('wage2')
A data.frame with 935 observations on 17 variables:
wage: monthly earnings
hours: average weekly hours
IQ: IQ score
KWW: knowledge of world work score
educ: years of education
exper: years of work experience
tenure: years with current employer
age: age in years
married: =1 if married
black: =1 if black
south: =1 if live in south
urban: =1 if live in SMSA
sibs: number of siblings
brthord: birth order
meduc: mother's education
feduc: father's education
lwage: natural log of wage
As with WAGE1.RAW, there are some clear inconsistencies among the variables tenure, exper, and age. I have not been able to track down the causes, and so any changes would be effectively arbitrary. Instead, I am using the data as provided by the authors of the above QJE article.
Used in Text: pages 64, 106, 111, 165, 218-219, 220-221, 262, 310-312, 338, 519-520, 534, 546-547, 549, 678
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(wage2)str(wage2)
Wooldridge Source: F. Vella and M. Verbeek (1998), “Whose Wages Do Unions Raise? A Dynamic Model of Unionism and Wage Rate Determination for Young Men,” Journal of Applied Econometrics 13, 163-183. I obtained the data from the Journal of Applied Econometrics data archive at http://qed.econ.queensu.ca/jae/. This is generally a nice resource for undergraduates looking to replicate or extend a published study. Data loads lazily.
data('wagepan')data('wagepan')
A data.frame with 4360 observations on 44 variables:
nr: person identifier
year: 1980 to 1987
agric: =1 if in agriculture
black: =1 if black
bus:
construc: =1 if in construction
ent:
exper: labor mkt experience
fin:
hisp: =1 if Hispanic
poorhlth: =1 if in poor health
hours: annual hours worked
manuf: =1 if in manufacturing
married: =1 if married
min:
nrthcen: =1 if north central
nrtheast: =1 if north east
occ1:
occ2:
occ3:
occ4:
occ5:
occ6:
occ7:
occ8:
occ9:
per:
pro:
pub:
rur:
south: =1 if south
educ: years of schooling
tra:
trad:
union: =1 if in union
lwage: log(wage)
d81: =1 if year == 1981
d82:
d83:
d84:
d85:
d86:
d87:
expersq: exper^2
pages 480, 494-495, 505
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(wagepan)str(wagepan)
Wooldridge Source: Economic Report of the President, various years. Data loads lazily.
data('wageprc')data('wageprc')
A data.frame with 286 observations on 20 variables:
price: consumer price index
wage: nominal hourly wage
t: time trend = 1, 2 , 3, ...
lprice: log(price)
lwage: log(wage)
gprice: lprice - lprice[_n-1]
gwage: lwage - lwage[_n-1]
gwage_1: gwage[_n-1]
gwage_2: gwage[_n-2]
gwage_3:
gwage_4:
gwage_5:
gwage_6:
gwage_7:
gwage_8:
gwage_9:
gwage_10:
gwage_11:
gwage_12:
gprice_1: gprice[_n-1]
These monthly data run from January 1964 through October 1987. The consumer price index averages to 100 in 1967.
Used in Text: pages 405, 444-445, 671.
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(wageprc)str(wageprc)
Wooldridge Source: These data were reported in a New York Times article, December 28, 1994. Data loads lazily.
data('wine')data('wine')
A data.frame with 21 observations on 5 variables:
country:
alcohol: liters alcohol from wine, per capita
deaths: deaths per 100,000
heart: heart disease dths per 100,000
liver: liver disease dths per 100,000
The dependent variables deaths, heart, and liver can be each regressed against alcohol as nice simple regression examples. The conventional wisdom is that wine is good for the heart but not for the liver, something that is apparent in the regressions. Because the number of observations is small, this can be a good data set to illustrate calculation of the OLS estimates and statistics.
Used in Text: not used
https://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781111531041
str(wine)str(wine)