Mixed model PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
Message/Author
 Aletta Nonyane posted on Friday, January 19, 2007 - 8:10 pm
Hi
Can you please help me with specifying a simple model with 1 fixed intercept and 1 random intercept (corresponding to a cluster called pattern) as well as residual error. The outcome variable is loghdl. Is the following correct? The results give a correct estimate for the mean loghdl (i.e fixed intercept) but the random intercept for pattern and residual error don't match those of a conventional mixed model. Can you please suggest a better way of fitting this simple model?

CLUSTER IS pattern
ANALYSIS
TYPE IS TWOLEVEL RANDOM
MODEL: %WITHIN%
loghdl
%BETWEEN%
loghdl; ! I know this is not necessary


Thanks
 Linda K. Muthen posted on Saturday, January 20, 2007 - 3:40 pm
You do not need RANDOM in this case to estimate a random mean. I suspect you are not using maximum likelihood in the other program and this is why the results do not match. If you have further questions, please send your Mplus input, data, output, the output from the other program, and your license number to support@statmodel.com.
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: