< >
Gabriele wrote
I do a probit regression in a cross section of individuals that are
from many countries (I have abouth one thousand of observations for
each country). For each individual I have a variable where it's
indicated his country. I desire to obtain a predicted probability
for the dependent variable not at individual's level but at county
level. How can i do?
In the enclosed, imagine that the individual observations for each
company belong to individuals. Your 'country' is my 'company', the
group with which the 'individual' is affiliated.
webuse grunfeld,clear
bys company: egen invmu = mean(invest)
bys company: g hi = invest > invmu
probit hi mvalue kstock
predict double hihat, pr
bys company: egen prcomp = mean(hihat)
list invest hi hihat prcomp if company < 3
Kit Baum, Boston College Economics and DIW Berlin
http://ideas.repec.org/e/pba1.html
An Introduction to Modern Econometrics Using Stata:
http://www.stata-press.com/books/imeus.html
*
* 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/
