st: RE: marginal effects in MNL model

[Diane Dancer <diane.dancer@sydney.edu.au>]

HI

I am quite new to Stata and am gradually working out how the programs etc work but am now very stuck.
I am estimating an MNL model using weights and a cluster variance.  The model all works and gives me good results.
However when I add the commands for the marginal effects as specified in the help directory I get no results and a comment about a bracket..
I am sure it is something quite simple but cannot do it.

The program is as follows:- 
#delimit

mlogit ord hv105 hv1052 male foothill mountain
kids5 hhsize femalehh wealth2 wealth3 wealth4 wealth5              
pprim psechigher pmissing [pw=wght], vce(cluster clus);
outreg2 using ouputv12.doc, nolabel append;
margins, dydx(") predict(outcome(1));
margins, dydx(") predict(outcome(2));
margins, dydx(") predict(outcome(3));

The output after the model is as follows.
. outreg2 using ouputv12.doc, nolabel append;
ouputv12.doc
dir : seeout

. margins, dydx(") predict(outcome(1));
> margins, dydx(") predict(outcome(2));
) required
r(100);

end of do-file

r(100);

I would be so grateful if anyone can help me.

Thanks
Diane Dancer


*
*   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/