st: question on -margins- after -clogit-

[Wei HAN <hanweigrace@gmail.com>]

Dear all,



I estimated the same specification as Gertler (1987) "Are user fees
regressive" function (6) using -clogit-. The outcome is a discrete
choice of health facility, e.g. private clinic, public clinic, public
hospital. Then I need to compute the price elasticity for each health
facility. Just as Gertler(1987), price component enters the regression
with its quadratic term, i.e. "ln(y-p)" and "ln(y-p)*ln(y-p)" [y
denotes income; p denotes price]. I want to ask whether -margins-
works in this case or not.

Many thanks in advance

Wei
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/