RDU posted on Monday, November 24, 2008 - 10:19 pm
Hello. I am working with a data set consisting of students nested within schools. I created a school-level (cluster-level) dummy variable for predominantly black schools, and I wanted to model this variable as a function of both student-level and other school or cluster-level predictors. So in the Mplus framework, is it better to treat this as a multilevel logistic model, or would it be more appropriate in this case to run a standard logistic regression? Thank you.