Mike Wazowski wrote:
is there a way in stata to estimate a simultaneous model with two dependent
variables that represent proportions? as suggested on
http://www.stata.com/support/faqs/stat/logit.html, i can do it for a single dv
with
glm ...., link(logit) family(binomial) robust
a search of statalist archives for "simultaneous and proportion" did not return
any meaningful queries.
i have cross sectional data only (one time period).
--------------------------------------------------------------------------------
Perhaps you could use -cluster(panel_id)- with -glm- (or -xtgee- analogously),
or you could fit a linear model after a variance-stabilizing transformation,
such arcsine-square-root.
Joseph Coveney
*
* 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/
