Re: st: series of teffects on multiple outcomes

[László Sándor <sandorl@gmail.com>]

Thanks, Billy. I am not sure that the same applies to multivalued
treatments following Cattaneo (2010). And of course, the built-in code
is much faster — though it looks like it need to be rerun.

Thanks!

On Fri, Sep 6, 2013 at 6:12 PM, William Buchanan
<william@williambuchanan.net> wrote:
> You should be able to do this with some of the user-written PSM/PSA programs.  Additionally, you could always do things manually; there are examples on the UCLA website for Murnane, R. J., & Willett, J. B. (2010) Methods matter: Improving causal inference in education and social science. New York City, NY: Oxford University Press.
>
> HTH,
> Billy
>
> Sent from my iPhone
>
> On Sep 6, 2013, at 15:51, László Sándor <sandorl@gmail.com> wrote:
>
>> Hi,
>>
>> I wonder if I could make it faster to -teffects aipw- multiple outcome
>> variables one after another. If I am correct, the regression
>> adjustment need to be rerun for different outcomes, but the treatment
>> prediction need not be. Is there a way to leverage one run for
>> another?
>>
>> What I have in mind is, in "pseudocode":
>>
>> teffects aipw (outcome1 controls) (multilevel_treatment predictors), SAVEPW
>> teffects aipw (outcome1 controls) (), USEPW
>>
>> Thanks,
>>
>> Laszlo
>> *
>> *   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/
>
> *
> *   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/

*
*   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/