Re: st: can stata perform ridge regression

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

At 10:14 PM 2/13/2004 +0800, rghuang wrote:
> when multicollinearity,it is not suitable to use ols regression.but can 
> use ridge regression,can stata do it?if it can not,how stata deal with 
> multicollinearity?
First off, it is still suitable to use OLS.  Estimates remain 
unbiased.  There is almost always some degree of multicollinearity, so how 
problematic multicollineairity is depends on how extreme it is.

-findit ridge regression- yields a few hits; I can't vouch for how good 
they work.  Greene notes in his Econometric Analysis, 4th edition, p. 258 
that ridge regression produces biased estimators and hence has seen little 
practical use.

For some general discussions on diagnosing and dealing with 
multicollinearity, see

http://www.nd.edu/~rwilliam/xsoc593/lectures/l03.pdf

http://www.ats.ucla.edu/stat/stata/modules/reg/multico.htm

There have also been some recent discussions of multicollinearity on 
Statalist; search the archives.

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