I am conducting a study on the rates of return to female students at 2 year
and 4 year colleges using the NELS-88 dataset, a nationally representative
sample of eighth-graders were first surveyed in the spring of 1988 and then
resurveyed through four follow-ups in 1990, 1992, 1994, and 2000. The
follow-up studies were designed to observe how the eighth grade experience
affected later educational and occupational attainment.
I will estimate the rates of return using OLS and will control for ability,
family background, student characteristics such as race/ethnicity and for
occupation.
Hoever, before estimating the model I must address the possibility of
sample selection bias. I therefore intend to use a 2 step estimation
method similar to Heckman (1979) and Kane and Rouse (1994) where the first
step is the participation equation (in the case of Heckman) or
self-selection into a 2 or 4 year college (in the case of Kane and Rouse).
The probit results are then used as an additional regressor in OLS.
The problem is I do not know how to do a probit analysis using STATA. I
have only used STAT for OLS.
Kindly help
please respond using my other two addresses
[email protected], [email protected]
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
