----- Original Message -----
From: "Henry Sauermann" <[email protected]>
To: <[email protected]>
Sent: Monday, August 18, 2003 4:27 PM
Subject: st: heteroskedasticity and oprobit/ologit
> Hello stata-champions,
>
> I am still looking for a way to test and correct for heteroskedasticity
> after ordered (!) probit or logit regression in stata. Does anybody know of
> a way to do in stata or knows a stata add-on?
>
> Thanks a lot for your help,
> Henry Sauermann
>
>
Statalist,
In a previous reply to Henry's post, I suggested the use of the robust option to
compute Huber/White errors. As David Drukker kindly pointed out to me, this
will not solve Henry's problem. The model will be inconsistent is the presence
of heteroskedasticity and therefore, computing a robust covariance matrix for
inconsistent estimators is not useful.
I hope no one was misled by my previous reply,
Scott
*
* 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/
