Although the number of already known (3 loci) and replicated loci (1) was not large enough to build a predictive model, we inspected the features of both groups of AREDS SNPs (replicated and non-replicated) for insights that might facilitate efficient selection of SNPs for replication (Table S1 and Table 5).
In our previous study using this tumor model [39], we inspected the surviving animals for an additional 3-month period and recorded only 2 cases of mortality within more than 200 animals.
To evaluate the sources of model misfit, we inspected the modification indices and noted that the primary sources were in the Vitality and Mental Health subscales, particularly at the within-person level, such that the positive items loaded together.
To show the potential effect of study design on model performance, we inspect the sample covariance diagnostic (13) for this dataset for the Poisson case for a reduced number of sites and/or visits.
We inspected all models for statistically significant interactions between severity variables, child age and episode duration.
To address this, we inspected every model in the ensemble and found that each predicted an above-additive increase in cyclin D expression (data not shown).
We inspected the model fit by considering the Hosmer and Lemeshow goodness-of-fit test statistic (good fit indicated by statistic not being significant at p < 0.05), and by considering the explained variance through the Nagelkerke R-Square.
We inspected the final models for collinearity based on condition indices and variance inflation factors, as described in Belsey, Kuh, and Welsch [ 45]; collinearity did not appear to be a problem in either model.
Turning back to the linear response of the model, we now inspect the sensitivity as a function of b and g K 1.
For the task of visually inspecting these models, we advocate the use of Cutaways: an illustrative technique to emphasize important structures or parts of the model by selectively discarding occluding parts, while keeping the contextual information.
