# Re: st: curvilinearity with moderator

 From Stas Kolenikov To statalist@hsphsun2.harvard.edu Subject Re: st: curvilinearity with moderator Date Wed, 21 Oct 2009 11:19:37 -0500

```If your question really is about A, then why do you need B in here at
all? And why do you need A^2? If C is categorical, then there is not
much sense in saying "Introducing C shifts A to the right". You could
say that for different levels of C the conditional distributions of A
are different, and that can be checked with ANOVA or its
non-parametric versions (Kruskal-Wallis). Please clarify what your
research questions here is.

On Tue, Oct 20, 2009 at 3:56 PM, P K <statistics_2009@yahoo.de> wrote:
> Hi,
>
> I am trying to examine the moderating effects on a curvilinear relation between variable A and B in a multiple regression,
>
> ie.
>
> A ->B : positive coeff.
> A^2 ->B : negative coefficient
>
>
> I want to examine whether introducing variable C shifts the whole distribution of A to the right.
>
> Variable A and B are continuous
> Variable C is categorical.
>
> For examing such a moderating role of variable C, I think that only the interaction of AxC   has to be significant and positive - is that right?
>
> Or does the interaction betwen A^2 xC also has to be significant (in that case, this would imply that the distribution of A is not only shifted to the right, but also that the shape of the distribution has changed, correct?)
>
> Any advice is appreciated.
> Thanks,
> Pat
>
>
>
>
>
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>

--
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/
```