controlling for baseline data in multiple logistic regres.

Moderators: statman, Analyst Techy, andris, Fierce, GerineL, Smash

cdmr
Posts: 1
Joined: Sun Dec 25, 2011 8:01 am

controlling for baseline data in multiple logistic regres.

Postby cdmr » Sun Dec 25, 2011 8:16 am

Hi all,

I have a data set from a randomized control trial study testing an intervention. My data include both baseline and post-intervention measures. I will need to use multiple logistic regression as I have more than 2 predictors with a dichotomous outcome variable. I have two questions:

1-) How can I control for the baseline measure or compare it with the post-intervention measure in multiple regression?

2-) How can I compare my experimental and control group in the multiple logistic regression? Basically would selecting cases who belong to experimental group and control group and running two analyses for each be ok?

This is the first time I am using multiple logistic regression, therefore, your help will be greatly appreciated!

Thanks a lot in advance!
GerineL
Moderator
Posts: 1477
Joined: Tue Jun 10, 2008 4:50 pm

Re: controlling for baseline data in multiple logistic regre

Postby GerineL » Wed Jan 18, 2012 5:05 pm

cdmr wrote: 1-) How can I control for the baseline measure or compare it with the post-intervention measure in multiple regression?
add baseline measure in step 1 rest in step 2 and further.
2-) How can I compare my experimental and control group in the multiple logistic regression? Basically would selecting cases who belong to experimental group and control group and running two analyses for each be ok?
no it would not be ok, use interaction for that (or use amos but thats not a part of spss, its a separate program)

Who is online

Users browsing this forum: No registered users and 1 guest

cron