Re: st: Re: Partial R-squares

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

At 04:08 PM 9/14/2004 -0500, Yulia Marchenko wrote:

> The partial R-square (or coefficient of partial determination) measures the
> marginal contribution of one explanatory variable when all others are
> already included in the model. For example, in the above example only 7.7%
> of the variation in mpg is reduced by adding weight to the model when length
> is already in the model. However, such interpretation is not valid, for
> example, if your explanatory variables are collinear.
Brief discussions of partial and semipartial correlations can be found at

http://www.nd.edu/~rwilliam/stats1/x94.pdf

http://www.nd.edu/~rwilliam/stats1/Semipartials-Stata.pdf

Better still is to read the Cohen and Cohen book that is cited in the notes 
(the notes use the 1975 version of the book but a newer edition was 
released in 2002 or 2003.)

This is one of those things I tend to teach "because it is there", i.e. it 
shows up in computer printouts and some authors may use them but it is not 
something I find terribly useful myself.  It does help to make it clear why 
adding more variables to a model may produce little change in R^2.

-------------------------------------------
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/