Sentence examples for model performance statistics from inspiring English sources

Model performance statistics indicated that the curve number method performed slightly better than the Green and Ampt method.

This study attempts to deliver transparency in terms of access to data and model performance statistics.

Model performance statistics suggested a relatively strong relationship between actual and estimated mean ring density (Table 4).

This paper demonstrates how model performance statistics can be used to calibrate and/or validate hydrodynamic models in a more objective way.

Details of the model development are provided along with a Calculation Report for each chemical prediction; the latter reporting model performance statistics within both local and global applicability domains, as well as metrics for determining confidence in the chemical prediction.

Validation of results against monitoring records, and model performance statistics demonstrated that despite the extremely sparse data, the approach used in this study was capable of simulating the cumulative impacts of agricultural land reclamation reasonably well.

We evaluated model performance with statistics commonly used for judging the performance of SDMs: the Area Under the Curve of the Receiver Operator Characteristic Function (AUC) [ 82], the proportion of presences and absences correctly categorized (pcc), the proportion of presences correctly predicted (sensitivity), and the proportion of absences correctly predicted (specificity).

Nevertheless, estimating the reliability of confidence estimates for relatively weak models is perhaps an even more critical need than making such estimates for models with strong performance statistics.

The count scale in Figure 6A is logarithmic, so the number of positive predictions in the area of overestimation is usually small for unbalanced models with acceptable performance statistics.

In general, the simplest models had lower performance statistics.

Furthermore, models were developed using contemporaneous monitoring data (rather than extrapolating backward using input data from more recent years), and all models were evaluated, with performance statistics equal to those obtained in models for recent years.