power analysis after ttest

[robertekraut]

I'm trying to import the means and stds from a two sample ttest into power twosample, but the power command seems to accept only typed-in numbers and not r() style pointers to numbers. Am I doing something wrong or is the power command?

Here is what I tried:

run the ttest
. ttest s_wellbeing if gysj_inexper , by (gysj_yn)
... output deleted

confirm that I can retrieve means and standard deviations using r() notation
. dis r(mu_1) " " r(mu_2) " " r(sd_1) " " r(sd_2)
3.3537638 3.4037035 1.0217724 .9781072

power returns an error when I use the results from ttest in r() form
power twomeans r(mu_1)r(mu_2), sd1(r(sd_1)) sd2(r(sd_2))
means must contain numbers
r(198);

But it works fine if I type in the numbers directly
power twomeans 3.3537638 3.4037035, sd1(1.0217724) sd2(.9781072)

Performing iteration ...
... results deleted

[Leonardo Guizzetti]

You need to wrap your macro results in single quotes, as below, so that Stata can de-reference the macros before executing the power command.

power twomeans `r(mu_1)' `r(mu_2)', sd1(`r(sd_1)') sd2(`r(sd_2)')

You may find it helpful to read the following documentation: -help quotes- and -help macro-.

[robertekraut]

Thank you very much. That solved my problem. rek