Estimates random slopes per cluster PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
Message/Author
 Simon de Jong posted on Tuesday, April 30, 2019 - 3:17 pm
Is it possible for multilevel logistic regession analyses to obtain the estimates of the random slopes per cluster? For example, I know that the slope of IV1 is positively associated with DV1, and varies across countries, but I don't know whether the direction is the same for all countries.

Thanks in advance!
 Bengt O. Muthen posted on Tuesday, April 30, 2019 - 4:00 pm
Yes, just request FSCORES (factor scores).
 Simon de Jong posted on Wednesday, May 08, 2019 - 12:23 am
Thank you for your quick reply. I have a follow up question: Is it possible to test whether these cluster-estimates significantly differ from 0 (or each other)? Or does such a test not make sense because the parameter estimates are realizations of the random effect?
 Bengt O. Muthen posted on Wednesday, May 08, 2019 - 2:27 pm
Right, it doesn't make sense because you are considering a random variable values, not parameters. The interest should instead be of the variance of the random effect is zero or not.
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: