Mike,
As I understand it, the generalized residual for the probit model is:
u = [pdf(xB)/cdf(xB)*(1 - cdf(xB))]*[y - cdf(xB)]
When y = 1
u = pdf(xB)/cdf(xB)
when y = 0
u = - pdf(xB)/(1 - cdf(xB))
where pdf and cdf are the p.d.f. and c.d.f. of N(0,1)
In Stata:
probit y x
predict xb, xb
gen gen_residual = cond(foreign == 1,
normden(xb)/norm(xb), -normden(xb)/(1-norm(xb)))
Hope this helps,
Scott
----- Original Message -----
From: "Michael Furukawa" <[email protected]>
To: <[email protected]>
Sent: Thursday, December 25, 2003 10:39 AM
Subject: st: Generalized (probit) residuals
> Can anyone help me with how to calculate the generalized (probit)
> residuals based on Gourieroux et.al. (1987, Journal of Econometrics)?
>
> thanks,
> Mike Furukawa
> PhD Candidate
> Wharton/University of Pennsylvania
>
*
* 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/
