Hello,
I've been using umx for estimating bivariate sex-lim models (umxSexLim), which has been extremely helpful. After estimating the possible models, the scalar model had the best fit to the data.
However, there is one weird result, that I don't seem to understand its source.
For trait X (when testing a bivariate model for X and Y), in the scalar model, the heritability standardised estimates are .04 and .05 for males and females, respectively. However, when estimating the homogeneity model, the joint heritability estimate for males and females is .14 for the same trait X (that is, much higher than both estimates). Furthermore, when testing the scalar model in a univariate analysis just for trait X, the heritability estimates are .12 for males and 0 for females (which make sense according to the MZM(.55)-DZM(.31) and MZF(.09)-DZF(.21) correlations).
Does it make sense that when adding a trait to the analysis, only one estimate would be that different?
The correlations for males and females combined are rMZ: 0.4, rDZ(only same-sex): 0.25, rDZ(with OS): .18 (the OS correlation is .10 [-.04 - .24]). That is, it seems the combined correlations indicate a larger heritability estimate that is not represented in the estimates presented by the scalar model.
The scalar model was selected by fit indices and tests - that is it’s the most parsimonious model that did not affect model fit. However, as the correlation between DZ-OS correlation is almost 0, doesn’t it make more theoretical sense that a qualitative model will be selected? (-2LL: scalar 7060.65, non-scalar 7059.88, AIC: scalar 2542.65, non-scalar 2557.88).
Another thing - I also checked variance differences between MZ and DZ, and there are significant differences in variances both when looking only on DZ-SS (SD=.57) and on all DZ(SD=.56) (compared to MZ, SD=.64, variable is standardized). What are the implications of these results in how we view the model results?
I would appreciate your expert's thoughts and opinions in understanding these results, and how can they make sense.
Thanks,
Noam.
Printer-friendly version
Data where DZ is twice MZ correlation (MZF r= .09 DZF r= .21) suggest very small samples where your power to detect sex differences is so small that you'd be better of saying this and merging the DZs?
As to things like the bivariate scalar model showing a small heritability for one trait (~ .05 for males and females), but the homogeneity model showing .14, this seems what you'd expect given the Males showed heritability and the females didn't?
Adding a second trait can help the model detect true signal (a bit like adding more manifests latent trait model aids estimation of the latent. Trying to improve the measurement model, and trap measurement error there might help.