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: RE: Panel Data with Clustered Errors

From   "Wooldridge, Jeffrey" <>
To   <>
Subject   st: RE: Panel Data with Clustered Errors
Date   Mon, 28 Feb 2011 17:19:41 -0500

An easy but not entirely satisfying solution is to estimate the
so-called population average effects by GEE, using the -xtgee- command.
It allows clustering at any level but, of course, is not the random
effects logit model.

I noticed that several Stata commands for nonlinear models do not allow
clustering at a higher level. I'm hoping this changes in Stata 12 as it
is easy to add.


-----Original Message-----
[] On Behalf Of Dmitriy
Sent: Monday, February 28, 2011 4:28 PM
To: statalist
Subject: st: Panel Data with Clustered Errors

Dear Listers,
I have a large panel dataset which contains clustered errors. I am
trying to estimate a binary outcome model via -xtlogit- re (random
effects) using Stata 11. There seem to be no option for clustered
errors. Can anyone suggest a viable solution?

*   For searches and help try:

*   For searches and help try:

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