Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

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

st: RE: xtlogit, xtgee and matsize

From   "Nick Cox" <>
To   <>
Subject   st: RE: xtlogit, xtgee and matsize
Date   Wed, 3 Mar 2010 18:28:32 -0000

You need a bigger Stata, or to program your own version of -xtlogit-
without using Stata's matrices. Getting the first is more money but much
less work. 


Nikolaos Pandis

I would like to ask the following:

I have a dataset of around 20000 observations with clustered data. 

I am running the xtlogit [. xtlogit outcome arm,i(cluster) or nolog re]
command with the re options and runs fine. However, if I try to run the
same command with -pa- option or by using the corresponding -xtgee-
command I get the following  error message:

"matsize too small -- must be able to set matsize to at least 1380"

I use the IC version and I can only go up to matsize 800. Is there an
easy way around this problem?

*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index