Re: st: Test Results in Table

[Tim Wade <wadetj@gmail.com>]

Toby, see -postfile- and the example in the help. Depending on the
test you are doing, the p-values may be saved as an r-class or e-class
result. To see, type -return list- and -ereturn list- after the
command. You can then use -postfile- to accumulate and  save the
p-values in a temporary stata data set, then -outsheet- to a text
file. If the p-values aren't saved you can calculate them from other
saved results (e.g., z-scores).

Tim

Sent from my iPod

On Aug 19, 2011, at 6:49 AM, Toby <spiegeldesaster@googlemail.com> wrote:

> Dear List-Readers,
>
> I have a problem, that I am pretty sure of that most of you have a
> handy solution for.
>
> I want to program a Do-File which performs multiple statistical test
> with different subsets of my dataset. Since there is a multitude of
> subsets I programmed  a for-loop to perform these test pretty quick.
>
> So far, so good. No comes the "though" part. I want to save different
> values of this statistical tests (p-Values etc.) in a table that is
> somehow exportable  into another program (for example txt or xls).
> What I can do and have done is save these values in new generated
> variables, but this is definitefly not helping to export, or do I have
> a fundamentally wrong approach here? I tried a bit with tabout and
> estout, but figured out that they are only helpful for estimation
> methods and  summary statistics.
>
> I heard of the matrix program, but I am not quite sure how to apply it
> to my problem.
>
> What do you recommend?
>
> Kind Regards,
> Toby
> *
> *   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/