Mike Zyphur posted on Friday, October 29, 2010 - 6:05 pm
I am wondering if anyone has worked out a model specification for Mplus that mimics what Neale et al. do in Mx when they work with extended twin family data. Their models use data from MZ males, MZ females, DZ males, DZ females, and mixed DZ twins. Also included are parents, children, spouses, etc.
It sounds like they use a multi-group specification where they estimate aggregate correlations for each type of relationship (e.g., correlation for all uncles and all nephews). However, it's not altogether clear in their papers what they're doing. I can provide cites if interested.