I guess you had no luck in either step because you didn't bother to use the
help system:
-search singular value decomposition- points you toward the mat svd command
-search variance covariance matrix - returns many items and right near the
top a FAQ shows what you need.
Please check the help system in the future before asking the list. Here's a
one-time free pass:
regress y x1 x2 x3
mat vcv=e(V)
mat list vcv
mat svd u w v = vcv
mat list u
mat list w
mat list v
Michael Blasnik
[email protected]
----- Original Message -----
From: "Michael A Massoglia" <[email protected]>
To: <[email protected]>
Sent: Tuesday, January 06, 2004 12:55 PM
Subject: st: var-cov matrix-SVD
> I need to produce the variance-covariance matrix for a set of regression
> parameters, and then do singular value decomposition on the matrix.
>
> Is that possible in stata? I have had no luck, with either step, and
would
> be most appreciate of an simple example.
> Thank you
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
