Re: st: test with Interaction terms (#) in regression

[Rodrigo Badilla <rodrigo.badilla@gmail.com>]

Hi all,

Thanks to all people that did reply me, my english is no so good and
probably  my last message was not clear, my objective with this
i.x#c.z ...is just have a regression with continous variables (not
different categories) , finally i found this test to run

testparm i.x#c.z

thanks again
Rodrigo


\-/    > ><((((º>`·.¸¸.·´¯`·.¸¸><((((º>¸.
 /\
/--\    ´¯`·.<º))))><·´¯´
\-/         Atte.
 /\         Rodrigo Badilla.
/--|        Biologo Marino.
            62202469


2012/12/4 Philip Ender <ender97@gmail.com>:
> Rodrigo Badilla <rodrigo.badilla@gmail.com> wrote:
>
> I am runing a regression analisys with Interaction terms:
> reg y i.x#c.z
> now i d like run a test for the this interaction in differents categories.
>
> ------------------------
>
> You have a categorical by continuous interaction which tells you
> whether the slope of y on z differs among levels of x.  The easiest
> way of looking at this is
>
> . margina x, dydx(z)
>
> You have only one categorical and one continuous variable so I'm not
> sure what you mean when you say, "I d like run a test for the this
> interaction in differents categories."
>
> --
> Phil Ender
> UCLA Statistical Consulting Group
> *
> *   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/

*
*   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/