Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: cholesky vs matpowersym for FGLS transformation in Mata
From
Gordon Hughes <[email protected]>
To
[email protected]
Subject
Re: st: cholesky vs matpowersym for FGLS transformation in Mata
Date
Thu, 26 Apr 2012 10:18:07 +0100
Use -cholesky()-.
Routines for Cholesky decomposition are very efficient and
numerically stable. Stata's version uses LAPACK code which is the
best available. In practice, -matpowersym()- uses the
eigenvalue/eigenvector decomposition, which is inherently more
expensive than the Cholesky decomposition as it does not take
advantage of the special structure of your problem.
Gordon Hughes
[email protected]
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/