Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: interaction

From   "maartenbuis" <>
Subject   Re: st: interaction
Date   Wed, 28 Sep 2005 18:28:03 -0000

--- Ricardo Ovaldia <ovaldia@y...> wrote:
> I remember seen something on statalist or SJ about
> getting a single test statistic or p-value for the
> interaction term when the variables involved have many
> levels (for example: continuous*categorical). I have
> looked for it but can not findit. Does anyone recall
> this?

I don't recall that discussion but try:

sysuse auto
xi: reg price i.rep78*mpg
test  _IrepXmpg_2  _IrepXmpg_3  _IrepXmpg_4 _IrepXmpg_5

which test the hypothesis that all interaction terms are simultaniously 
equal to zero

Hope this helps,

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index