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: Error in using xttest2

From   Anirudh Shingal <>
To   "" <>
Subject   st: Error in using xttest2
Date   Mon, 9 Aug 2010 11:48:23 +0200

Dear All,

I have a dynamic heterogeneous non-stationary unbalanced panel with N=14 and T=25 and several explanatory variables.

When I use xttest2 to test for cross-sectional dependence, STATA says that the test cannot be done as the "correlation matrix of residuals is singular."

If I use xtcsd instead it works but technically it is incorrect to use this as N is not greater than T for my sample.

Why does this happen and what should I do?

Many thanks,

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index