Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: GEE versus Probit.

From   natasha agarwal <>
Subject   st: GEE versus Probit.
Date   Sun, 30 Oct 2011 14:31:17 +0000

Dear All,

I was trying to estimate the Average Partial Effects for a balanced
panel for a probit model following Mundlak (1978) corrections as
described in Woolridge.

I find it very difficult to do the same using the 'probit' command as
I do not understand how to scale the coefficients. However, I can so
the same using the 'glm' or 'xtgee' command linking to the probit

However, I fail to understand the subtle difference between the
'probit' and the 'glm' or 'xtgee' command.

If anybody can help me with this, I would be very grateful.

*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index