A. Dyrlund posted on Thursday, May 18, 2006 - 5:09 am
I am conducting a multiple groups CFA. My first group has n=2315 and my second group has n=418. Is the large difference in sample sizes going to influence they chi-square results? Also, is the first group used to first estimate the parameters and the second group fitted to the estimates of the first group?
You will obtain chi-square results for both groups together and each group. You will have more power in the first group due to the larger sample size. The model is fitted simultaneously to the data for both groups. Some measurement parameters are held equal across groups by default. This is described in Chapter 13 of the Mplus User's Guide.