Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: question about the interaction term


From   David Hoaglin <dchoaglin@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: question about the interaction term
Date   Thu, 25 Apr 2013 14:11:23 -0400

Dear Vic,

The output is very helpful.  Thank you.

The effects of frbc, homo, and frbc_homo must be interpreted as "after
adjusting for the contributions of [the other predictors in the
model]."  With that in mind, none of those three predictors has a
significant effect (at the .05 level).  Thus, the effect (slope) of
frbc does not differ between the homo=0 group and the homo=1 group.
(I do not see where "frbc is significant in the testing.")

It would be reasonable to remove frbc_homo from the model, to see
whether frbc has a significant slope (overall) and whether homo is
significant.  If both of those variables are significant, then the
same slope on frbc applies to both groups, and the two groups differ
in level (i.e., intercept).

David Hoaglin

On Thu, Apr 25, 2013 at 11:21 AM, ZHVictor <victerzj2@hotmail.com> wrote:
> Dear David,
> Thank you!This is the output in stata
>              |               Robust
>              |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
> -------------+----------------------------------------------------------------
> performance  |
>         frbc |  -.8474035   .4923128    -1.72   0.085    -1.812319    .1175119
>    frbc_homo |   .3386407   .6860396     0.49   0.622    -1.005972    1.683254
>         homo |   .0977946   .4812832     0.20   0.839    -.8455031    1.041092
>        board |   .0076623   .0470874     0.16   0.871    -.0846274     .099952
>        indep |  -.5825246   .6177608    -0.94   0.346    -1.793314    .6282644
>        audit |   -.002093   .0926196    -0.02   0.982    -.1836241     .179438
>          roa |   1.704518   1.494709     1.14   0.254    -1.225058    4.634093
>      finance |   .6123755    .430509     1.42   0.155    -.2314066    1.456158
>     leverage |   .0535289   .6785705     0.08   0.937    -1.276445    1.383503
>         size |   .0170652   .1050801     0.16   0.871     -.188888    .2230183
>          mtb |   .0545689    .027851     1.96   0.050    -.0000181     .109156
> inst_holding |   .6830099   .6363314     1.07   0.283    -.5641768    1.930197
>        _cons |  -1.426625   1.042372    -1.37   0.171    -3.469637    .6163864
> test frbc+frbc_homo=0
>  chi2(  1) =    1.87
>          Prob > chi2 =    0.1718
>
> frbc is a continuous variable and homo is a dummy variable. Basically, I want to see whether frbc has different effect in the homo=0 group vs homo=1 group.
> The interaction term frbc_homo is insignificant but the frbc is significant in the testing "frbc+frbc_homo=0"
> Thank you!
*
*   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/


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