First, although we used cross-validated training and in some cases additional activity data for model selection, due to the large number of models we built, it is possible that some models perfectly predict all training data, albeit by chance.
The log-linear Rasch model perfectly predicted the strength of the association between EORTC items and rest scores (Table 1, see supplementary data).
If the independent variables in a model perfectly predicted the outcome, then the Nagelkerke pseudo R2 would equal 1. Due to the relatively high number of statistical tests performed throughout the manuscript, and the resulting increase in likelihood of a type 1 error (false positive), a more stringent value of p ≤ 0.01 was used to denote statistical significance throughout all analyses.
A comparison between experimental and numerical results indicates that the numerical model perfectly predicts the variations in both temperature and complex modulus until a certain strain level, where the damage, thixotropy or other factors have not appeared yet.
For example, both data sets analysed here used saturated models which perfectly predicted the input correlation matrices, so the fit indices based on the discrepancy between observed and SEM-predicted correlation matrices obtained maximum values possible, but this was not particularly informative.
They range from 0.5 to 1.0, with 0.5 representing a model no better than chance and 1.0 a model that perfectly predicts.0.7 is typically considered reasonable and 0.8 strong [ 19].
Successful design of chemotherapy drug scheduling requires the availability of an accurate mathematical model that perfectly predicts the number of cancerous cells and describes effects of treatment.
The maximum value of Q is 1, representing that the model could perfectly predict the phenotypes.
Such decoupling means that the effect of temperature on sex ratio is not perfectly predicted by current models based solely on the effect that temperature has on development, revealing that the potency that temperature has to influence developmental rate differs somewhat from its potency to induce sex determination as described below.
While both the final mass and the protein content were almost perfectly predicted in the new model, the results were much less accurate for the old model, particularly for fat deposition (a large discrepancy existed), probably due to incorrect temperature dependence in the model as well as the numerical instabilities.
