Re: st: Comparing results from two separate t-tests

[Richard Goldstein <richgold@ix.netcom.com>]

I suggest a regression with an interaction between treatment and group.

Rich

Geoff Wallace wrote:
> Dear All,
>
> I have had problems trying to test for whether the treatment effects for 
> two groups of respondents (conservatives and liberals) in a social 
> science experimental questionnaire I am using are significantly 
> different. I used the -ttest- command to obtain the difference of means 
> across the treatment and control group first for the conservative 
> respondent subsample and then repeated the procedure for the liberal 
> respondent subsample. I should also note that I used the –unpaired- 
> option for each command since the data are not paired. The output from 
> the two -ttest- commands yields a separate treatment effect for each 
> subsample. However, I am having trouble figuring out how to use Stata to 
> perform a corresponding ttest on the two separate difference of means. I 
> tried using -est store- after each -ttest- command, but as I expected 
> this option does not appear to work with –ttest-.
>
> Any help would be much appreciated.
>
> Best, Geoff
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/