Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: -adjust- with interaction terms?


From   "Tim Wade" <wadetj@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: -adjust- with interaction terms?
Date   Mon, 15 Oct 2007 15:53:32 -0400

Hi Daniel, I'm not sure if this is what you want exactly, but instead
of generating the varaible as you did below, can you simply use:
predict if mbpos==1? I think it gives you the same results. Tim



On 10/14/07, Daniel Waxman <dan@amplecat.com> wrote:
> Statalist,
>
> Is there any way to use -adjust- with interaction terms involving the
> term being adjusted?
>
> In the following example:
>
> . xi: logistic is_dead  i.mbpos*zlog i.mbpos*zero
>
> where mbpos is 0/1
>
> One can adjust for mbpos=1, by:
>
> gen pr_mb1= invlogit(_b[_Imbpos_1] + _b[zlog]*zlog + _b[_ImbpXzlog_1]*zlog /*
>                       */ + _b[zero]*zero + _b[_ImbpXzero_1]*zero + _b[ _cons])
>
>
> But this is quite error-prone and somewhat cumbersome.
>
> Suggestions?
>
>
> Thanks.
>
> Daniel
> *
> *   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/
>
*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index