Re: st: Conformability error following margins command

[Maarten Buis <maartenlbuis@gmail.com>]

On Tue, May 1, 2012 at 5:14 PM, Paul Spin wrote:
> I am working with Stata11/SE for Windows. I am attempting to estimate
> partial effects for each covariate of a multinomial logistic regression.
> Unfortunately I keep running into a conformability error - r(503) - after
> running the margins command.
>
> --------------------------
>
> svyset [pw=weight], vce(brr) brrweight(wboot*)
> xi:svy: mlogit unmetneed i.age i.sex, b(0)

One error I see is that when using -margins- you should _not_ use the
-xi- prefix. You can and should still prefix categorical variables
with -i.-.  In essence, -margins- uses information you give it through
the new factor variable notation (see: -help fvvarlist-), so in order
to use -margins- correctly you need to use the factor variable
notation correctly. Using the -xi:- prefix means you are using the
older and obsolete factor variable notation.

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/