Re: st: probit residuals

[Paul Millar <paul.millar@shaw.ca>]

You can easily generate the residuals manually.  I assume that you 
want the squared residual based on the probability value (as opposed 
to the actual prediction of zero or one).

sysuse auto
probit  foreign price mpg weight
predict phat
gen resid=(foreign-phat)^2

- Paul

At 02:34 PM 16/05/2007, you wrote:

> Maarten L. Buis wrote
> > --- Philip Ender wrote:
> > > > > Stata's logit camand can compute several types of residuals but
> > > > > probit does not compute any residuals at all. Why is probit
> > > > > different from logit with respect to residuals?
> > --- Maarten L. Buis wrote
> > > > You can get those residuals when estimating that model with -glm-.
> > --- Philip Ender wrote:
> > > Thanks Maarten, that helps a lot.  But it still leaves unanswered why
> > > you can't compute residuals after the probit command.
> > I know that my answer didn't answer your question, and neither does
> > this answer, the true answer is that I don't know the answer, just a
> > quick workaround.
> > Maarten "doesn't know all the answers" Buis
> Maarten-
>
> You are being much too harsh on yourself.  So far, there is only one
> question that you don't know the answer to. Maybe your signature could
> be...
>
> Maarten "knows all but one answer" Buis
>
> --
> Phil Ender
> Statistical Consulting Group
> UCLA  Academic Technology Services
> *
> *   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/
*
*   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/