st: Re: Variance-Covariance Matrix

[Christopher Baum <kit.baum@bc.edu>]

<>
On Jan 5, 2014, at 2:33 AM, Adrian wrote:

> I'm sorry for asking such a simple question but unfortunately I
> couldn't find an answer. How do you get the variance-covariance matrix
> in Stata?
> I know it's available in postestimations using e(V) but in my case
> there is no estimation. Specifically  I got two variables each with
> length of 306 that I transformed into a matrix
> 
> .mkmat x1 x2, matrix(test1)
> 
> Now there must be some way to calculate the variance-covariance matrix
> in an efficient way as in other known mathematical software.
> 
> Something like:
> .matrix cov test1
> 
> Am I missing something?
> Does anyone have an idea to get the v-cov matrix in some way? Help is
> very much appreciated. Thanks.

There is no need for matrix commands, Mata, or regression formulae. 

. sysuse auto
(1978 Automobile Data)

. corr price mpg,cov
(obs=74)

             |    price      mpg
-------------+------------------
       price |  8.7e+06
         mpg | -7996.28   33.472

. ret li

scalars:
                  r(N) =  74
             r(cov_12) =  -7996.282858200665
              r(Var_2) =  33.47204738985561
              r(Var_1) =  8699525.97426879

matrices:
                  r(C) :  2 x 2

. mat li r(C)

symmetric r(C)[2,2]
            price         mpg
price     8699526
  mpg  -7996.2829   33.472047




Kit Baum
Professor of Economics and Social Work, Boston College, Chestnut Hill MA, USA
DIW Research Professor, Department of Macroeconomics, DIW Berlin, Berlin, Germany
baum@bc.edu  |  http://ideas.repec.org/e/pba1.html












*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/