Re: st: xtlogit RE on Stata 7 vs Stata 9

[Richard Williams <Richard.A.Williams.5@ND.edu>]

At 09:22 PM 11/16/2006, Regina T. Riphahn wrote:
> Hello,
>
> I have a dataset and run xtlogit with RE in Stata 9. Then I save the 
> data as a Stata7 dataset using saveold and run xtlogit with RE under 
> Stata 7. The two xtlogit results differ.
>
> The two data summaries are identical in Stata 7 and Stata 9. The 
> results of a simple logit (without xt) are also identical.
>
> My questions are:
> (1) why do the results differ and
> (2) can I obtain the Stata 9 results with the Stata 7 software?
I don't really know, but according to -help version-, if you set 
version to less than 9

Commands xtintreg, xtlogit, xtprobit, xtcloglog, xtpoisson, and 
xttobit revert to using nonadaptive Gauss-Hermite quadrature rather 
than adaptive quadrature.  In addition, option 
quad()           (modern name intpoints()) comes back to life.

So, in Stata 9, you might try something like version 
7:xtlogit...  and see if you get the same results as version 7.  Or, 
alternatively, see if version 7 lets you use nonadaptive 
Gauss-Hermite quadrature.

-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX:    (574)288-4373
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW (personal):    http://www.nd.edu/~rwilliam
WWW (department):    http://www.nd.edu/~soc 
*
*   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/