Re: st: average marginal efefcts after mi

[Sunniva Andersen <andersensunniva6@gmail.com>]

Thank you Morten,

I have tried to changes the code, but there is still an error.

mi estimate, post:logit employment alder barn
margins, dydx ( alder barn)

warning cannot perform check for estimable functions. e (sample) does
not identify the estimation sample.


mi estimate, or:logit employment alder barn
margins, dydx ( alder barn)

last estimates not found.


Any further advice about this?
Sunniva




2011/7/4 Maarten Buis <maartenlbuis@gmail.com>:
> On Mon, Jul 4, 2011 at 9:28 PM, Sunniva Andersen wrote:
>> Trying to obtain margins after mi command in stata 11.
>> below my code and error message.
>>
>> mi estimate:logit employment alder barn
>> margins, dydx ( alder barn)
>>
>> error message last estimates not found
>
> You'll get results by typing
>
> mi estimate, post : logit employement alder barn
>
> However, I am not sure whether the results mean the same thing as in
> normal non-imputed datasets. One problem I can imagine is that average
> marginal effects need to be averaged, and I am not sure whether your
> marginal effects are averaged over the appropriate sample.
>
> Alternatively you can interpret the odds ratios, which I expect to be
> less problematic
>
> mi estimate, or : logit employement alder barn
>
> Hope this helps,
> Maarten
>
> --------------------------
> Maarten L. Buis
> Institut fuer Soziologie
> Universitaet Tuebingen
> Wilhelmstrasse 36
> 72074 Tuebingen
> Germany
>
>
> http://www.maartenbuis.nl
> --------------------------
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/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/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/