
Message/Author 

Jan Fax posted on Friday, September 19, 2008  5:47 am



Hello 3 questions how to relate the Mplus ex10.6 output to the parametric MLLCA approach suggested by Vermunt (2003). For the clusterlevel covariate w, there is an effect of .79 on the factor capturing the betweenvariation of the withinlevel latent class intercepts. Q1: Can this estimate be used to answer a question like "how does w affect the log odds of belonging to (withinlevel)latent class 1 vs. 2"? (such an interpretation is given in the vermuntarticle, example on "educational research", effect of the schoollevel variable CITO, page 232). Q2: If so, how? Q3: Can I estimate intraclass correlations to check whether the lc intercepts differ substantially between groups? How? Many thanks! 


Q1. Q2Q3. This relates directly to 2level logistic regression which we discuss in our courses. See the handout for Topic 7 at http://www.statmodel.com/newhandouts.shtml where slides 4449 go through an example and slide 49 discusses the level 2 effect in 3 different ways. The example concerns a random intercept. With a continuous level2 covariate w you can consider a 1 SD change in w and how much higher or lower the class probabilities are due to this change. Such probabilities can then be converted into odds. 

Back to top 

