Sentence examples for for each model was calculated using from inspiring English sources

The root mean square error of prediction (RMSEP) for each model was calculated using {text{RMSEP}} = sqrt {frac{{mathop sum nolimits_{i = 1}^{n} (y_{i - } hat{y}_{i} )^{2} }}{n}},where y i is the measured and (hat{y}_{i}) is the predicted value.

For the ML analysis, the appropriate substitution model was calculated using ProTest program, version 1.3 [ 67].

Model discrimination for each of the models was calculated using area under ROC curve.

ΔAIC values for the Felsenstein84 nucleotide substitution model were calculated using PAUP* and ModelTest.

NADH binding energies for the resulting models were calculated using the Ligand Interactions subroutine.

Coefficients of determination (R) for the robust regression models were calculated using STATA rregfit command.

Additive, dominant and recessive models were calculated using linear and logistic regression models for the quantitative and categorized traits respectively.

c P for heterogeneity was calculated using multivariable model a for each cohort.

For each of the models the accuracy was calculated using 10-fold cross validation.

P-values for phosphoproteomic data was calculated using a ratio error model [ 64].

For non-linear models, the BMDL was calculated using the (iterative) profile likelihood method.