Species biogeography did not appear to affect predictive performance and all models performed well statistically with receiver operating characteristic area under the curve (AUC) ranging from 0.87 to 0.98.
Statistical measures of model performance and associated graphical analysis of the final specifications indicated that the models performed well in terms of accounting for a relatively large proportion of variation (61 88%), unbiasedness and predictive ability (e.g., temporal invariant patterns in absolute and relative prediction errors).
For PM2.5 and PM10, the models performed well in urban and rural areas and across seasons, though performance varied somewhat by region of the conterminous U.S. For PM2.5 10, model performance was poorer, particularly in the Southeast and Southcentral regions.
A clinical prediction rule was considered if the resulting model performance was sufficient (high negative predictive value, NPV) on the validation set, however, no models performed well enough to consider developing a clinical prediction rule.
Both models performed well.
Both models performed well for lynchets.
The developed models performed well predicting volumetric water contents between 0.55 and 0.9 cm− cm− 3.
Though visual comparison indicated that all models performed well, the analytical comparison revealed the true differences between them.
Despite the low frequency of poor outcomes both models performed well, with receiver operating characteristic curves of 0.75 for maternal outcomes and 0.78 for infant outcomes.
The models performed well in predicting the global mean surface temperature and had some predictive value in the Atlantic Ocean, but they were virtually useless at forecasting conditions over the vast Pacific Ocean.
In the regression setting, both GP and SVR models performed well, yielding MAEs as low as 0.66 +- 0.08 log units (clustered CV) and 0.51 +- 0.3 log units (normal CV).
