st: Imputation routine 'ice' produces conformabilitiy error with micombine, mlogit, and prchange

[Barry Ames <barryames@yahoo.com>]

an update of the routine 'mice'.  It produces 'm' data
sets with the imputed variables plus identifiers _i
and _j.

   I run mlogit with prchange and then mlogplot.  With
the 'ice' routine, once you have created the imputed
data sets (my 'm' = 5), you put micombine in front of
the mlogit command.  So I have

'micombine mlogit depvar indvar' etc.

 Mlogit runs, but prchange produces a "conformability
errror" (503).   This happens even if I only have one
independent variable.  If I treat the 5 imputed data
sets as one big non-imputed data set, mlogit and
prchange run fine.

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/