Re: st: testing for significant changes in r squared within

[Maarten buis <maartenbuis@yahoo.co.uk>]

--- On Wed, 23/2/11, Jan Mammen wrote:
> I would like to test the hypothesis of a nonlinear
> relationship by adding first a linear term, afterwards the
> squared and finally the cubic term of multinationality. I
> am looking for a possibility to show that the inclusion of
> the squared and cubic term significantly improves the model.

I addition to the comments made by Nick I'd like to add that
I like linear splines for such non-linearity tests. The big
advantage is that they are easiet to interpret than square
and cube terms and you are less likely to end up with 
improbable shapes than when you add a cube term.

You can make the spline terms using -mkspline-, see: 
-help mkspline-.

For the interpretation of spline terms, see:
<http://www.stata.com/statalist/archive/2011-02/msg00270.html>

You can test for linearity, by just using -test- on the 
hypothesis that the effects of the different terms are equal.

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------


      

*
*   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/