mModelPerformance: Performance of a multinomial prediction model

Description Usage Arguments Value References

Description

Apparent (= within sample) predictive performance of a multinomial prediction model. Works with the mlogit and mnlogit packages.

Usage

1

Arguments

fit

A model fit object.

...

...

Value

An object of class "mPerformance".A list containing several types of performance measures: discrimination (M-index or multiclass AUC), overall performance (Brier score and various R squares: Cox, Nagelkerke and McFadden) and calibration ().

References

Nagelkerke NJ. A note on a general definition of the coefficient of determination. Biometrika. 1991 Sep 1;78(3):691-2. McFadden D. Conditional logit analysis of qualitative choice behavior.

Brier GW. Verification of forecasts expressed in terms of probability. Monthly weather review. 1950 Jan;78(1):1-3.

Hand DJ, Till RJ. A simple generalisation of the area under the ROC curve for multiple class classification problems. Machine learning. 2001 Nov 1;45(2):171-86.


VMTdeJong/mPerformance documentation built on May 14, 2019, 7:42 a.m.