Raheem Paxton posted on Monday, May 07, 2007 - 6:42 pm

Hi, I'm trying to find out if the variance/covariance matrix is the same between groups and wasn't quite sure how to proceed in Mplus. Was told to constrain all factor loading to 1, all item variances to zero, etc. Could you please show me where I am going wrong. THANKS Program ANALYSIS: TYPE = GENERAL; ITERATIONS = 5000; H1Iterations = 5000; MODEL: PROS BY PDBp1_1@1PDBp2_1@1PDBp3_1@1PDBp4_1@1PDBp5_1@1; CONS BY PDBc1_1@1PDBc2_1@1PDBc3_1@1PDBc4_1@1PDBc5_1@1;

I think you may have misunderstood the advice you were given. I think the advice was to put one factor behind each latent variable. This is not necessary in Mplus. If you want to look at a model of covariances, use the WITH option.