st: Nlogit RUM and unbalanced data error

["Jeff Smith" <jsmith94@utk.edu>]

To all,

I am trying to estimate a nested logit model using the nlogitrum command
(per Stata Journal 2:3).  My data is formatted as necessary for a
conditional logit estimation and it runs the clogit command just fine.
However, after specifying the tree structure

	. nlogitgen type = option(choose: 1|2, no_choose: 3)
	new variable type is generated with 2 groups
	label list lb_type
	lb_type:
           1 choose
           2 no_choose


and then verifying that the structure is correct

	. nlogittree option type
	tree structure specified for the nested logit model
      	  top --> bottom
	        type        option
	--------------------------
      	choose              1
                                2
	      no_choose           3


I get the following:

	. nlogitrum asc spec_mec spec_hec sold_lec sold_mec payment, group(id)
nests(option type)

	tree structure specified for the nested logit model
      	  top --> bottom
	        type        option
	--------------------------
      	choose             1
                               2
	      no_choose          3
	unbalanced data
	r(459);


ASC is my constant variable and the rest of the variables define the choice
set.  My alternative specific choices are effects coded.  Any help on what
the "unbalanced data" error message means would be most appreciated.  I have
searched online and through the manuals to no avail.

Thanks in advance for the assistance,

Jeff Smith

*
*   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/