Dear Stata users,

I have a question regarding the one-sided p-value in outreg2, which I use to export my tables to Word.
Following the user guide, this is not an option specified there.
Therefore my question: Would it be possible to produce the one-sided p-value instead of the two-sided p-value in outreg2?

My research contains 3 groups, for which I hypothised that the effects for Group1 & Group 2 > Group 3 and Group1>Group2.
I use 2 dummies: D1 (treatment 1==1) and D2 (treatment 2==1) and I want to know the effects of these dummies to identify the ITT.

I used the following code to generate the table output.

Code:
bys wave: outreg2 using "C:\Users\Nelleke\Documents\Universiteit\Master jaar 2\Gender", word stats(coef se pval ci) alpha(0.001, 0.01, 0.05) symbol(***, **, *) asterisk(pval) dec(3) replace: reg WomenempIndexstandardised D1 D2 $b_controlvar, vce(robust)
I read in the manual that it would be possible to use stored estimates, which I tried:

Code:
sort wave
by wave: regress WomenempIndexstandardised D1 D2 $b_controlvar, vce(robust)
return list

bys wave: outreg2 [r(p_u)] using "C:\Users\Nelleke\Documents\Universiteit\Master jaar 2\Gender", word stats(coef se pval ci) alpha(0.001, 0.01, 0.05) symbol(***, **, *) asterisk(pval) dec(3) replace: reg WomenempIndexstandardised D1 D2 $b_controlvar, vce(robust)
However this provides the following error: factor-variable and time-series operators not allowed r(101);

Could anyone explain to me what went wrong and how I could obtain the one-sided p-values? I would already be very happy with a hint in the right direction.