Structural equation modelling was used to evaluate model fit, as well as direct and indirect pathways.
Effects of species on the model fit as well as on the structure of the residuals were tested but effects were small.
TLI and CFI values over.90 indicate good model fit, as well as RMSEA values of.05 or lower [ 37].
Table 1 shows the parameter values obtained in the final model fit as well as the mean parameter values obtained in the bootstrap procedure.
Several methods for overall model fit, as well as fit within deciles of predicted costs, were used to test the predictive ability of the models.
In addition to these fit indexes, the item bias DIF (differential item functioning) was verified, since it can determine decrease in model fit, as well as measurement inappropriateness.
The coefficients of variations for the structural parameters are all below 30%% in both the original model fit as well as in the bootstrap procedure.
For example, we have shown that an ancestral root distribution coupled to the context-dependent model does not improve model fit as much as a decoupled ancestral root distribution does.
An assumption concerning the evolutionary behaviour of sites in an alignment that typically greatly improves model fit as well as phylogenetic tree reconstruction is that of gamma-distributed rate-heterogeneity, although typically used in non-coding sequence data.
Similarity between the theoretical and assigned probabilities is considered to indicate good model fit, as are respondents having a high posterior probability for a single group (measured using means of the group with the highest posterior probability).
On the other hand, even reducing the number of time points to 4 per subject (Sparse scenario) seems to have little influence on the quality of the model fit as can be judged from the fraction of misclassifications presented here.
