Re: st: results of interaction term

[Richard Williams <Richard.A.Williams.5@nd.edu>]

At 03:43 PM 3/17/2005 -0500, Jian Liu wrote:
> Dear list members,
>
> I've a question regarding interpretation of the results of interaction 
> term from multiple regression model.
> before introducing interaction term, the results from MR were:
>  x1 (continuous)  significant
>  x2 (binomial)      significant
> after introducing the interaction term x1x2, the results from MR were:
> x1 significant with no change of coefficient
> x2    not significant with a change of coefficient
> x1x2 not significant
>
> So how do we interpret the results as such? thanks for your help.
The interpretation of main effects gets trickier once you start including 
interaction terms; in particular, you probably shouldn't get too concerned 
about x2 becoming insignificant because it has a different meaning once you 
add the interaction term.  Centering vars can help make interpretation 
easier.  This is discussed a bit at

http://www.nd.edu/~rwilliam/xsoc593/lectures/l52.pdf

Based on what you are saying, it sounds like you want to leave the 
interaction term out.


-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX:    (574)288-4373
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW (personal):    http://www.nd.edu/~rwilliam
WWW (department):    http://www.nd.edu/~soc

*
*   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/