Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: MI estimate error


From   Maarten Buis <[email protected]>
To   [email protected]
Subject   Re: st: MI estimate error
Date   Fri, 27 May 2011 15:55:37 +0200

On Fri, May 27, 2011 at 3:41 PM, Michael Beck <[email protected]> wrote:
> But when I exchange the dependent variable trying to compute the following
>
> mi estimate, post: mlogit manote staat2 staat3 staat4 staat5, baseoutcome(2)
> rr vce(cluster XYZ)
>
> (manote being the grade in math)
>
> Stata is telling me:
>
> mi estimate: omitted terms vary
>    The set of omitted variables or categories is not consistent between m=1
> and m=5; this is not
>    allowed.  To identify varying sets, you can use mi xeq to run the
> command on individual
>    imputations or you can reissue the command with mi estimate, noisily
>
>
> I have no idea what the problem is and how to deal with it.

I guess it means the following: -mlogit- needs to exclude one
reference category. If the reference differs across models, than the
coefficients cannot be compared, and averaging them would result in
completely meaningless numbers. In which case, Stata is issuing an
error instead. You see if this is the case by looking at -tab m
manote, missing- to see if the imputation model created any "weird"
grades.

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany


http://www.maartenbuis.nl
--------------------------

*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index