Throughout all the lead times, however, the hybrid W-SAS-MP model performed best with CE values of 0.911 and 0.909, respectively, for prediction lead time of 1 day and 0.588 and 0.570, respectively, for prediction lead time of 5 days at Stations 17836 and 17837, respectively, at the model testing (validation) phase.
Within Maxent processing, 75% occurrence points (164) were randomly selected for training model, and the rest 25% points (54) were used for model test and validation.
75% occurrence points were randomly selected for training model, and the rest 25% points were used for model test and validation.
The socio-cognitive model of test validation (Weir 2005) is one such model and provides a theoretical framework that allows test designers and researchers to evaluate and modify tests through a cyclical process of development.
Of the total suspected points, 25% were randomly excluded from modeling and used for model testing and validation.
Because using the same data for model testing and validation leads to overfitting and deflates the estimated error rate, we used 10-fold cross-validation on a randomly selected 75% training sample for model training.
Model tests and validation results and discussion are given in Sect.
The model testing and validation showed that the error in prediction is in the range between−2% and +2%.
The validation of the model tested over the validation time period resulted in a mean absolute error of 10.6%, but in a more real-time manner of up to 1-2 wearlierrliearlier
In the analytic work for this paper two-thirds of the available cases were randomly identified for model derivation (n = 390,356), one-third were reserved for model re-test validation (n = 195,532).
