Anastasia Semykina and Jeffrey M. Wooldridge, "Estimation of Dynamic 
Panel Data Models with Sample Selection," Journal of Applied 
Econometrics, Vol. 28. No. 1, 2013, pp. 47-61.

The data come from the Panel Study of Income Dynamics (PSID, 
http://simba.isr.umich.edu/), years 1981 to 1992 (also contains earnings 
data from 1980). The sample consists of 579 white females, who were 
followed over the considered period. In total, there are 6,948 
observations over the 12-year period (1981-1992).

Data are organized in the form of a long panel where columns represent 
variables and rows represent observations. Variable names and 
descriptions are provided below.

  obs:         6,948                          
 vars:            11
----------------------------------------------------------------------------
variable name   type   format   variable label
----------------------------------------------------------------------------
id              float  %9.0g    Individual identifier
year            float  %9.0g    Survey year
age             float  %9.0g    Calculated age in years (based on year and
		       		month of birth)
educ            float  %9.0g    Years of schooling
children        float  %9.0g    Total number of children in family unit,
		       		ages 0-17
s               float  %9.0g    Participation dummy, =1 if worked (hours>0)
lnw             float  %9.0g    Log of real average hourly earnings
lnw80           float  %9.0g    Log earnings in 1980              
agesq           float  %9.0g    Age squared              
children_lag1   float  %9.0g    Number of children in t-1
children_lag2   float  %9.0g    Number of children in t-2

These data are in the file sw-data.txt, which is an ASCII file in DOS 
format. It is zipped in the file sw-data.zip. Unix/Linux users should 
use "unzip -a".