RE: st: Multinomial Logit Model - Cramer Ridder Test

[Nick Cox <n.j.cox@durham.ac.uk>]

You are missing my point. To understand my point, you need to understand a bit about what Stata calls "version control". 

Perhaps you didn't follow my reading suggestions, or I wasn't explicit enough. 

I was speculating about the effect of the statement -version 7- at the head of -crtest- which may be forcing -mlogit- to behave old-style and so affect ignorance of factor variables. 

I have a better suggestion than my previous, or at least a more focused one. Clone -crtest- and edit the line which re-runs -mlogit- so that it starts 

version 11: 

That way, you insist on -mlogit- being called under version 11. If it doesn't work, I am out of ideas, but it is simple enough to try. 

Nick 
n.j.cox@durham.ac.uk 

Ian Li

I am already on version 11 of -mlogit-. 

. which mlogit
C:\Program Files (x86)\Stata11\ado\updates\m\mlogit.ado
*! version 11.0.8  11feb2011

> From: n.j.cox@durham.ac.uk
>
> My guess is that you are calling -mlogit- under version control, i.e. the initial -version 7- is biting you.
> It may be that changing that to -version 11- would be enough to fix the problem, but if you do that _you take full responsibility_, not me, nor the author of -crtest-!
>
> Despite its summary, the FAQ
>
> FAQ . . . . . . . . . . . . . . . User-written programs and Stata version
> . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . N. J. Cox
> 7/11 I have a certain version of Stata and have come
> across a user-written program that is apparently
> written for a later version of Stata. What are
> my options?
> http://www.stata.com/support/faqs/lang/version2.html
>
> is relevant to you in saying more about -version-.
>
> Nick
> n.j.cox@durham.ac.uk
>
> Ian Li
>
> Nick, the output from -trace- is copied below.
>
> - version 7.0

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/