Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: 3D Panel Probit


From   S.R.Copping@warwick.ac.uk
To   statalist@hsphsun2.harvard.edu
Subject   st: 3D Panel Probit
Date   Mon, 25 Feb 2008 17:43:24 -0000 (GMT)

Hi all,

Does anybody know how to run a panel probit regression in Stata 9.0, where
there are multiple observations for each time observation?

I have 70 countries, with data measured over 4 years (I still don't know
if Stata is able to overcome the curse of dimensionality, can I use t>4?),
but for each year a country votes 4 times and each vote can vary. The
dependent variable is a binary variable representing the vote, so a panel
probit appears sensible. I am not interested in a logistic or extreme
value distribution. For each year and country, the covariates obviously
have duplicate data because for example, annual GDP will not vary just
because of one vote, because it is annual.

I have tried inputting the data and running this regression and it seems
fine for a dataset that has been constructed as a panel, and which is run
under the program command of xtprobit vote gdp ... , re theta. I am not
sure if this is correct given the 3D nature of the dataset however.

Furthermore, does anybody know how to interpret the coefficients of such a
regression?

Any help will be appreciated,

Sam
*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index