Thank you Nick,
Yes indeed I meant in r().
Out of interest, how can one view the source code for the command as you
suggest?
Best wishes,
Miranda
Nick Cox wrote:
-pcorr- doesn't save in e(), as it is not an estimation command.
As the help makes explicit, it saves results in r().
You'd need to use Stata functions as indicated in the source code for
-pcorr-. So pick up r-class results and use functions such as -tprob()-.
to save explicitly.
But given an interest in P-values it's about as easy to use the
equivalent -regress- results.
Nick
[email protected]
Miranda Kim
I use stata version 11. I'd like to use pcorr to compute partial
correlation coefficients over several lists of variables. I'd like to
use the returned results for this, but I don't know how to generate the
p-values as these are not saved by Stata. Is there a simple way of
calculating these using the results saved in e()?
*
* 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/
*
* 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/
