# Re: st: Fixing an -ml model- syntax problem

 From Glenn Hoetker To statalist@hsphsun2.harvard.edu Subject Re: st: Fixing an -ml model- syntax problem Date Tue, 20 Feb 2007 11:53:27 -0600

Dear Clive,

Glad to read someone is using my code. It wasn't quite clear if the hitch you were hitting was in Allison's original code or in complogit. If it is the former, I don't see something right off the bat. If it is the latter, well, "Rats!" Actually, if it is the latter, we should probably take debugging off-line. Please email me directly and we can see what's up.

For those interested in such things, I commend to you the work of Richard Williams (http://www.nd.edu/~rwilliam/), particularly his oglm code for Stata and the affiliated working paper, "Using Heterogeneous Choice Models To Compare Logit and Probit Coefficients Across Groups," both discussed on his website. I have not yet had the chance to parse carefully all of Richard's results, but his work suggests that there may now be better ways to test for and address the issues raised by Allison than were available when I wrote complogit.

Best.

Glenn

Glenn Hoetker
Assistant Professor (Business, Law, Institute for Genomic Biology)
University of Illinois at Urbana-Champaign
217-265-4081
ghoetker@uiuc.edu

On Feb 20, 2007, at 2 /20/07 11:10 , Clive Nicholas wrote:

For fun, I thought I'd test out an old piece of Stata code I found in Allison (1999: 203-4) that fires up a logit model which takes into account unequal residual variation across groups. I'm sure it's just a minor thing, but I'm having problems running his Stata 6 routine, which utilizes -ml- code:

webuse union, clear
program define gplogit
version 6
args lnf theta delta
qui replace `lnf' =
\$ML_y1*`theta'*(1+`delta')
ln(1+exp(`theta'*(1+`delta')))
end
ml model lf gplogit (union = age black grade south) ///
(delta: black,nocons)
ml maximize

Using Glenn Hoetker's -complogit- routine shows there is residual variation and actions the above model. Unfortunately, all I get with this code is

invalid syntax
r(198);

which is rather puzzling, as I can't see a lot wrong. Can anyone solve this puzzle?

Clive Nicholas

Reference

Allison PD (1999) "Comparing Logit and Probit Coefficients Across Groups", SOCIOLOGICAL METHODS AND RESEARCH (28)2: 186-208.

___________________________________________________________
All New Yahoo! Mail – Tired of unwanted email come-ons? Let our SpamGuard protect you. http://uk.docs.yahoo.com/nowyoucan.html

*
* 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/
```