[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Has anyone experimented with the new survey versions of heckman and
I can not estimate the standard errors with SVYHECKMAN.
When I ran Heckman ignoring the survey design, stata does provide the
estimates for standard errors. However, in the first few iterations, the log
likelihood is not concave.
* For searches and help try: