No. What is left behind after -pwcorrs- is
just the last correlation it did.
What you want can be done in many other ways.
One is to use -makematrix- from SSC with the
-listwise- option.
Doing it from first principles is also
straightforward and has many advantages.
Nick
[email protected]
R.E. De Hoyos
> I am trying construct a pairwise correlation matrix that will then be
> multiplied (element by element) by the number of pairwise
> observations.
>
> F. Wolfe's -pwcorrs- command computes and displays the
> pairwise correlation
> matrix, however the correlation matrix (and the number of pairwise
> observations) are not being saved as post estimation matrices/macros.
>
> A solution for this can be to compute the pairwise correlation myself
> (presumably using -corr- within a loop), but I am almost
> certain that there
> is way in which I take advantage of F. Wolfe's -pwcorrs-.
*
* 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/
