Sentence examples for model performance estimates from inspiring English sources

Random forest code was written in Java for this study, and all statistical analyses (e.g., model performance estimates) were performed using R.

Also, Sensitivity and Specificity features were comparable to the predictive model performance estimated on cell lines by the bootstrapping protocol.

The blade model performance was estimated in terms of rotation torque coefficient and thrust coefficient.

In addition, the model performance in estimating diurnal VTEC variations was found to be better during low solar activity phases than during high solar activity phases.

However, the genetic algorithm technique was more effective with the ETa calibration while significantly reducing the model performance for estimating the streamflow (NSE: 0.32 0.52, PBIAS: ±32.73%, and RSR: 0.63 0.82).

Meanwhile, using the multi-variable technique, the model performance for estimating the streamflow was maintained with a high level of accuracy (NSE: 0.59 0.61, PBIAS: ±13.70%, and RSR: 0.63 0.64) while the evapotranspiration estimations were improved.

Model performance was estimated using leave-one-out cross-validation.

Risk model performance was estimated using a validated bootstrap bias-correction procedure.

Model performance was estimated with the Nagelkerke Pseudo- R2 statistic (a measure of explained variation in the model).

Predicted water and sediment concentrations of PAHs (SI Table S7) were used in the food web model to demonstrate overall model performance using estimated emission rates and physiochemical parameters without corrections or calibrations using water, sediment, or other measurements.

Model performance was estimated and compared as extra-sample via bootstrapping (100 replicates), considering out-of-bag distributions, and assessing significance via t-tests adjusted for sample overlap and multiple comparisons[ 39- 41].