# st: RE: one-sided p-value using test x1=x2

 From "Martin Weiss" To Subject st: RE: one-sided p-value using test x1=x2 Date Wed, 30 Sep 2009 19:35:16 +0200

```<>

Why don`t you take your cue from official Stata?

**************
webuse fuel3, clear
ttest mpg, by(treated)
reg mpg treated
te treated
**************

HTH
Martin

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of
itchiftc@rumms.uni-mannheim.de
Sent: Mittwoch, 30. September 2009 19:05
To: statalist@hsphsun2.harvard.edu
Subject: st: one-sided p-value using test x1=x2

Hello all,

can anyone help me how to calculate the one-sided p-value of a F-test
testing coefficients from panel regressions? (test x1=x2)
For example, I would like to test whether beta1<beta2 and not
beta1=beta2. Is it correct when I just divide the p-value by 2 when
testing beta1-beta2>0 and calculate (1-p-value/2) when testing
beta1-beta2<0? Does anything change when both coefficients are
negative? Do I need to take absolute values?

Sorry for bothering you with this rather simple question, but I was
not sure whether the FAQ contribution to one-sided tests
(http://www.stata.com/support/faqs/stat/oneside.html) applies to my
case, as I want to test the difference between two coefficients (and
not whether a coefficient is smaller or larger than zero or another
number).

Any help would be highly appreciated!

Regards, Ida

*
*   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/
```