*
*  Example 7.8 and 7.9
*  J. Wooldridge, Econometrics of Cross Section and Panel Data
*
*  Note: The sample data files include all required data transformations.
*        However, in many cases we show how these data transformations would
*        be created in RATS from the basic data, as this is something you will
*        need to know how to do in practice.
*
cal(panelobs=2)
all 366//2
open data gpa.xls
data(format=xls,org=columns) / term sat tothrs cumgpa major season frstsem crsgpa $
  crspop verbmath trmgpa hssize race hsrank id $
  spring female black white hsperc
*
linreg trmgpa / resids
# constant spring cumgpa crsgpa frstsem season sat verbmath hsperc hssize black female
*
* Test for serial correlation by rerunning the regression including the lagged
* residuals as an explanatory variable. This knocks out the first observation in
* each individual, so we get half the sample size. The frstsem and spring dummies
* are dropped from the regression. (When using RATS, it actually doesn't hurt to
* leave them in. RATS will detect the linear dependence and zero the coefficients
* and their standard errors).
*
linreg trmgpa
# constant cumgpa crsgpa season sat verbmath hsperc hssize black female resids{1}