compareAUC {lulcc}

Calculate the area under the ROC curve (AUC)

Description

Estimate the AUC for each ROCR::prediction object in a PredictionList object.

Usage

compareAUC(pred, ...)

## S4 method for signature 'PredictionList'
compareAUC(pred, digits = 4, ...)

## S4 method for signature 'list'
compareAUC(pred, digits = 4, ...)

Arguments

pred

a PredictionList object or a list of these

...

additional arguments (none)

digits

numeric indicating the number of digits to be displayed after the decimal point for AUC values

Details

The user can compare the performance of different statistical models by providing a list of PredictionList objects. Note that compareAUC should be used in conjunction with other comparison methods because the AUC does not contain as much information as, for instance, the ROC curve itself (Pontius and Parmentier, 2014).

Value

A data.frame.

References

Sing, T., Sander, O., Beerenwinkel, N., Lengauer, T. (2005). ROCR: visualizing classifier performance in R. Bioinformatics 21(20):3940-3941.

Pontius Jr, R. G., & Parmentier, B. (2014). Recommendations for using the relative operating characteristic (ROC). Landscape ecology, 29(3), 367-382.

See Also

PredictionList, ROCR::performance

Examples

## see PredictiveModelList examples