st: no ATET with teffects aipw

[Sarah Edgington <sedging@ucla.edu>]

Hello all,
I have some questions about the new teffects commands, specifically 
the doubly robust estimator aipw.

My first question is about the documentation for aipw command.  Page 
62 of the teffects manual makes it clear that the only two statistics 
that -teffects aipw- can produce are the average treatment effect 
(ate) and potential-outcome means (pomeans).  The average treatment 
effect among the treated (atet) is not listed as an option.  However, 
in the remarks section of aipw on page 63  it says "They compute the 
weighted means of the treatment-specific predicted outcomes, where 
the weights are the inverse-probability weights computed in step 1. 
The contrasts of these weighted averages provide the estimates of the 
ATEs. By restricting the computations of the means to the subset of 
treated subjects, we can obtain the ATETs."

Is this mention of the ATET in the remarks section of the aipw an 
error?  I did try using the atet option with aipw just to double 
check that it hadn't been excluded erroneously from the options 
section.  Predictably,I got an error message indicating that the atet 
option is not allowed.

This leads me to my second, more substantitve, question.  Why is the 
ATET not available using -teffects aipw-?
As a long time Stata user my assumption is that if a command doesn't 
allow an option there's a good reason for it.  I was wondering if 
someone could help offer some intuition for what the reason is in the 
case of aipw?

I know that I can get the atet using the ipwra doubly robust 
estimator.  However, I'd like to also have a clearer understanding of 
what aipw is doing and why the atet isn't available.

Thanks.

-Sarah  

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/