Goodness of fit of logistic regression models was tested with the Hosmer and Lemeshow Goodness-of-Fit Test [ 30].
Also, the significance of the models was tested using the analysis of variance (ANOVA).
The efficiency of the proposed models was tested against sixteen well-known empirical correlations.
Overfitting of the models was tested using 'dropterm' in R and based on the lowest Akaike information criterion score, no terms were removed from the models.
Further the predictive ability of Grunberg Nissan, Lobe, Krishnan and Laddha, McAllister (four-body) interaction viscosity models was tested.
The predictive ability of generated models was tested on a set of 52 compounds having broad range of activity.
Appropriateness of prediction models was tested with test data consisted of 16 experiments not pertaining to the training data.
The validity of the models was tested by carrying out Barker fits on the isothermal data available in the literature.
Each of the three models was tested with approach wind directions from 0° to 90°, in 15° increments.
The performance of the stepwise and PLS models was tested by cross-validation and the external test set prediction.
Different age models, CAM and MAM-3, were used to establish palaeodose and the robustness of these age models was tested using a bootstrapping technique.
