Re: st: AW: estimation of series of OLS regressions based on t-values from previous regression

[John Antonakis <John.Antonakis@unil.ch>]

The more the independent variables and the smaller the sample size, the 
higher the likelihood that you'll capitalize on chance.  Many good 
journals don't even consider manuscripts anymore than have used stepwise:

Thompson, B. (1995). Stepwise regression and stepwise discriminant 
analysis need not apply here: A guidelines editorial. Educational and 
Psychological Methods, 4, 525-534.

Best,
John
____________________________________________________

Prof. John Antonakis
Associate Dean
Faculty of Business and Economics
University of Lausanne
Internef #618
CH-1015 Lausanne-Dorigny
Switzerland

Tel ++41 (0)21 692-3438
Fax ++41 (0)21 692-3305
____________________________________________________



On 30.01.2009 14:24, Richard Williams wrote:
> At 03:31 AM 1/30/2009, Martin Weiss wrote:
>> <>
>>
>> sdm,
>>
>> you could try -stepwise- with the -lockterm1- option. This option forces
>> -stepwise- to hold on to the first term no matter what. You can 
specify this
>> first term with parantheses so it can include several covariates, in 
your
>> case x1- x200...
>
> I almost suggested the same thing.  One problem is that it might take 
an eternity to run.  Stepwise is going to drop one variable at a time, 
whereas sdm is willing to drop huge chunks at a time that don't meet the 
desired criteria.  Still, it might be worth trying using the lockterm1 
and pr(.05) options.
>
> My guess is that if somebody really wanted to, they could write a 
routine that looked at the t-values and then only kept those Xs that met 
the desired criteria.  (But I don't really want to so I'm not going to 
bother!)
>
> Of course, there are qualms about stepwise regression in general, let 
alone stepwise regression involving 200 variables.
>
>
> -------------------------------------------
> Richard Williams, Notre Dame Dept of Sociology
> OFFICE: (574)631-6668, (574)631-6463
> HOME:   (574)289-5227
> EMAIL:  Richard.A.Williams.5@ND.Edu
> WWW:    http://www.nd.edu/~rwilliam
>
> *
> *   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/

*
*   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/