neg.gmpa

See <code><a href="/link/error.fun?package=emil&version=1.1-6" rd-options="" data-mini-rdoc="emil::error.fun">error.fun</a></code>.

true

pred

When dealing with imbalanced classification problem, i.e. where the class
sizes are very different, small classes tend to be overlooked when tuning
parameters by optimizing error rate. Blagus and Lusa (2013) suggested to
remedy the problem by using this performance measure instead.

A toolbox for designing and evaluating predictive models with
    resampling methods. The aim of this package is to provide a simple and
    efficient general framework for working with any type of prediction
    problem, be it classification, regression or survival analysis, that is
    easy to extend and adapt to your specific setting. Some commonly used
    methods for classification, regression and survival analysis are included.

neg.gmpa: Negative geometric mean of class specific predictive accuracy

Description

Usage

Arguments

Value

References

See Also