I doubt very much that there is one true stepwise path.
Even those who like stepwise approaches
emphasise that the results of forwards and backwards
may -- usually will -- differ substantially.
As is often mentioned on this list, stepwise methods
have so many disadvantages that on reflection you
might abandon them altogether. There is a FAQ on
this point at
http://www.stata.com/support/faqs/stat/stepwise.html
Since that FAQ was written, Frank Harrell has written
up his critique in a book "Regression modeling strategies".
Nick
[email protected]
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]]On Behalf Of
> [email protected]
> Sent: 13 April 2004 08:23
> To: stata group mail
> Subject: st: stepwise regression
>
>
> Hi all,
> I have performed the sw (stepwise) regress in Stata, my
> results with backward
> or forward estimation is very different, but I know that
> shouldn't be so.
> My question is: is the Stata sw procedure the real stepwise
> estimation??!!
> It seems to me that the selection is based only on the
> significance and
> not on the marginal explainatory power of every single variable.
>
> Many many thanks.
>
>
> *
> * 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/
>
*
* 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/
