Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Ordinal Probit Scores


From   <Colin.LEWIS-BECK@oecd.org>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Ordinal Probit Scores
Date   Thu, 3 Jul 2008 14:49:08 +0200

Dear Statalist,

I have a question about the scores post-estimation command after running an
ordinal probit.  I am trying to calculate the value of the first derivative
for each observation of the ordered probit likelihood function with respect
to the intercept at the maximum likelihood estimates.  It seems like the
"predict scores" command does this, however, when I try to double check the
derivatives manually, I get different results.  My ordinal probit has 5
categories, and thus I get 4 scores.  I am trying to double check the scores
by using the following formula:

(Pdf(cut j - linear predicted scores) - pdf(cut j+1 - linear predicted
scores))/ (cdf(cut j+1 - linear predicted scores) - cdf(cut j - linear
predicted scores)).

I am not sure why I can't get the same results as Stata.

Any information you could provide would be much appreciated.

Thanks,

Colin

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index