We are trying to compute a Murphy-Topel variance estimate for a two-stage
model where the two stages are independent (different data sets) and the
second stage is a two-limit Tobit model which includes, as a predictor, a
linear index based on the coefficients obtained in the first-stage
results.
If I am not mistaken, besides the usual covariance matrices for the
coefficients for the first and second stages, the only thing we need to
compute is the matrix of cross-product derivatives for the second-stage
likelihood function summed across individual observations (see Greene,
Econometric Analysis (4th ed.), p. 135. Is there a straightforward way
for non-programmers to code this calculation in Stata? Has anyone done
something similar?
Thanks for your help.
*
* 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/
