Dear Marteen,
Thanks for the command; I'll try to use it.
Indeed, the confidence interval is enormous also.
Aga
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of maartenbuis
Sent: Wednesday, December 08, 2004 3:26 PM
To: [email protected]
Subject: Re: st: predicted probabilities
--- "Markiewicz, Agnieska" <Agnieszka.Markiewicz@e...> wrote:
> I would like to calculate the predicted probabilities of different
> outcomes after ologit. Since I have couple of explanatory variables, I
> would like to predict the effect on the probability of an outcome
> keeping the other variables constant.
The command -prgen- in Scott Long and Jeremy Freese's package spost
(-findit spost-) is what you are looking for.
> Another question is about the odds ratios after ologit. Some of them
> look reasonable but some reach 5000 what seems to me strange. What can
> be the reason of these results?
The odds ratio is e^(parameter), so the value can easily get very
large. Have you looked at the confidence interval?
Maarten
*
* 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/
