CPS1988 | R Documentation |
Cross-section data originating from the March 1988 Current Population Survey by the US Census Bureau.
data("CPS1988")
A data frame containing 28,155 observations on 7 variables.
Wage (in dollars per week).
Number of years of education.
Number of years of potential work experience.
Factor with levels "cauc"
and "afam"
(African-American).
Factor. Does the individual reside in a Standard Metropolitan Statistical Area (SMSA)?
Factor with levels "northeast"
, "midwest"
, "south"
, "west"
.
Factor. Does the individual work part-time?
A sample of men aged 18 to 70 with positive annual income greater than USD 50 in 1992, who are not self-employed nor working without pay. Wages are deflated by the deflator of Personal Consumption Expenditure for 1992.
A problem with CPS data is that it does not provide actual work experience.
It is therefore customary to compute experience as age - education - 6
(as was done by Bierens and Ginther, 2001), this may be considered potential experience.
As a result, some respondents have negative experience.
http://www.personal.psu.edu/hxb11/MEDIAN.HTM
Bierens, H.J., and Ginther, D. (2001). Integrated Conditional Moment Testing of Quantile Regression Models. Empirical Economics, 26, 307–324.
Buchinsky, M. (1998). Recent Advances in Quantile Regression Models: A Practical Guide for Empirical Research. Journal of Human Resources, 33, 88–126.
CPS1985
, CPSSW
## data and packages
library("quantreg")
data("CPS1988")
CPS1988$region <- relevel(CPS1988$region, ref = "south")
## Model equations: Mincer-type, quartic, Buchinsky-type
mincer <- log(wage) ~ ethnicity + education + experience + I(experience^2)
quart <- log(wage) ~ ethnicity + education + experience + I(experience^2) +
I(experience^3) + I(experience^4)
buchinsky <- log(wage) ~ ethnicity * (education + experience + parttime) +
region*smsa + I(experience^2) + I(education^2) + I(education*experience)
## OLS and LAD fits (for LAD see Bierens and Ginter, Tables 1-3.A.)
mincer_ols <- lm(mincer, data = CPS1988)
mincer_lad <- rq(mincer, data = CPS1988)
quart_ols <- lm(quart, data = CPS1988)
quart_lad <- rq(quart, data = CPS1988)
buchinsky_ols <- lm(buchinsky, data = CPS1988)
buchinsky_lad <- rq(buchinsky, data = CPS1988)