Unfortunately, -adjust- does not have predict option, but you can
-preserve-, -replace-, and -predict, ycond-.
The following generates the conditional expectation for 5 values of mpg with
the other variables at their means.
sysuse auto
preserve
qui heckman price mpg weight length , select(fore = trunk )
foreach v of varlist weight trunk length {
sum `v', meanonly
replace `v' = r(mean)
}
forv i = 10(10)50 {
replace mpg = `i'
predict ycond_`i', ycond
}
tabstat ycond*, stat(mean)
restore
Scott
> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of Christer Thrane
> Sent: Friday, April 07, 2006 9:22 AM
> To: [email protected]
> Subject: st: adjust after heckman
>
> Hi,
>
> Normally I use adjust (after -regress-) to predict the mean earnings for
> variuos combinations of my indeps.
> When doing this for -heckman- I suspect that adjust produces the
> prediction
> for the "latent" mean earnings
> (ie regardless of if a person actually is employed or not). However, I
> want
> to get the mean earnings for the
> variuos combinations of my indeps, condtitional on being employed (ie
> being
> observed).
>
> How do I do this?
>
> Best regards,
>
> Christer Thrane
*
* 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/
