I have an additional SEM question. I have a have a 2x2 factorial experiment with a DV and a couple of mediators.
Typically exogenous variables are correlated. In this case, I have 3 IVs: A, B, and the AxB interaction. However, I KNOW they are uncorrelated because I made them orthogonal when I built the experiment. Do I still need to correlate them in the model? I can get additional degrees of freedom if I specify that they are UNcorrelated. However, I have been given mixed feedback on this, with some people saying it is fine to fix their correlations at zero, while others saying this violates assumptions. If anyone has any feedback on this, it would be greatly appreciated.
In regression, the model is estimated conditioned on the observed exogenous variables. Their means, variances, and covariances are not model parameters. You should not mention these parameters in the MODEL command.