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]

RE: st: cholesky decomposition

From   Maarten buis <>
To   stata list <>
Subject   RE: st: cholesky decomposition
Date   Wed, 3 Nov 2010 20:02:09 +0000 (GMT)

--- Narasimhan Sowmyanarayanan wrote:
> I am trying to do the cholesky decomposition of the vce matrix in
> stata and am finding that it says its not positive definite. After
> running the regression I specify
> reg x y z
> matrix v = e(vce)
> matrix c = cholesky(v)
> I get the following error:
> "cholesky(): matrix has missing values"

There is no vce matrix, only a V matrix. You should have gotten
an error message immediatly after the line -matrix v = e(vce)-,
unless you are using an old version of Stata. Anyhow, you probably
want to use -matrix v = e(V)- instead.

Hope this helps,

Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen


*   For searches and help try:

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