Print

Print


you can use penalized logistic regression if you believe that the independents work largely independently, or factor analysis if you believe interactions to be important . 

On Jan 8, 2013 9:16 AM, "khizar azam" <[log in to unmask]> wrote:
Dear All Greetings,
 I had collected data from 260 respondents data in PASW 18 my QUSEIONNAIRE had 125 INDEPENDANT VARIABLES AND 1 Depandant variable(dichotomous). Is it Mandatory for me to do data reduction(Factor analysis) before making model? or should i use all the independant variables and let my software take care of rest and develop a logistic model for me( Stepwise) and (Enter). I think that if i dont do data reduction it wont affect my results to a large extent.
Any other recommended method of model development?
Thanks.
Sincerely
Khizar(Researcher)
 
You may leave the list at any time by sending the command

SIGNOFF allstat

to [log in to unmask], leaving the subject line blank.

You may leave the list at any time by sending the command

SIGNOFF allstat

to [log in to unmask], leaving the subject line blank.