Scale correction factor PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
Message/Author
 Shane posted on Sunday, November 16, 2014 - 3:15 pm
Is there a way of getting the variance of the linear predictor from a logistic multilevel model in MPLUS so that I can calculate a scale correction factor? I would like to make a comparison between 2 logistic multilevel models; the first with only a ‘between’ explanatory variable and the second with additional ‘within’ explanatory variables.
 Tihomir Asparouhov posted on Monday, November 17, 2014 - 3:36 pm
Try using output:tech4. That should have the variances of all the predictors.
 Shane posted on Wednesday, November 19, 2014 - 9:26 pm
I don't understand how to go from these results to getting the variance of the linear predictor.

many thanks

Shane
 Tihomir Asparouhov posted on Thursday, November 20, 2014 - 3:37 pm
I would assume Var(beta*X)=beta*beta*Var(X)

Perhaps you want to also look at the R-square for these regressions. You can see that using
output:stand;
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: