Re: st: ...stepwise regression...

[Ernest Berkhout <ernestb@seo.fee.uva.nl>]

At 11:48 13/04/2004, Christer.Thrane@hil.no wrote:
> Hi,
>
> Prior research and/or theoretical rationales and/or common wisdom are three
> much used sources for selecting independent variables in a regeression
> model...
>
> Remember Leamer's labelling of stepwise regression-- a.k.a. unwise
> regression
I totally agree with the most commonly expressed views on stepwise 
regression on this list. But for the purpose,
depending on what Fabio's 500 variables actually seem to measure, might a 
reduction of that number using factor analysis be a possibility? If so, the 
three above mentioned sources are still needed very much...!


*
*   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/