Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Questions on gologit2 (fitstat and test [mleq1=mleq2])

From   Richard Williams <>
Subject   Re: st: Questions on gologit2 (fitstat and test [mleq1=mleq2])
Date   Tue, 27 Sep 2005 09:05:32 -0500

At 08:03 AM 9/27/2005, Herve STOLOWY wrote:
Dear All:

I have two questions concerning -gologit2- (downloadable from SSC).

I have used -gologit- several times with the following commands:

xi, prefix(): gologit format size1 auditor_d standards_d for_list lev2 sales_int3 i.gics4


test [mleq1=mleq2].

With -gologit2- and the same command lines, I get two error messages:

. After -fitstat-: "-fitstat- does not work with the last model estimated".
. After test [mleq1=mleq2]: "equation mleq1 not found".

I read the help file of -gologit2- but I can't find the equivalent of the above commands. I am sure that I miss something, but my level of understanding is not good enough.
-fitstat- does not currently work with -gologit2-. Add the -v1- parameter to -gologit2-, e.g.

xi, prefix(): gologit2 format size1 auditor_d standards_d for_list lev2 sales_int3 i.gics4, v1

That should solve both your problems; if not get back to me. Also, for -test- commands, you can refer to equations by their number, e.g.

test [#1=#2]

That tends to be safest because you don't have to worry about how the equations are labeled. In gologit2, the default is to use the value labels of y for the equation labels, whereas in -gologit- the default is to label them mleq1, mleq2, etc.

Incidentally, there is more info on gologit2 at

The troubleshooting FAQ is at

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):
WWW (department):
* For searches and help try:

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