obsinfo: Classifiability of observations

Description Arguments Details Value Author(s) References See Also

Description

Some observations are harder to classify than others. It is frequently of interest to know which observations are consistenly misclassified; these are candiates for outliers or wrong class labels.

Arguments

object

An object of class evaluation, generated with scheme = "observationwise"

threshold

threshold value of (observation-wise) performance measure, s. evaluation that has to be exceeded in order to speak of consistent misclassification. If measure = "average probability", then values below threshold are regarded as consistent misclassification. Note that the default values 1 is not sensible in that case

show

Should the information be printed ? Default is TRUE.

Details

As not all observation must have been classified at least once, observations not classified at all are also shown.

Value

A list with two components

misclassification

A data.frame containing the indices of consistenly misclassfied observations and the corresponding performance measure.

notclassified

The indices of those observations not classfied at all, s. details.

Author(s)

Martin Slawski ms@cs.uni-sb.de

Anne-Laure Boulesteix boulesteix@ibe.med.uni-muenchen.de

References

Slawski, M. Daumer, M. Boulesteix, A.-L. (2008) CMA - A comprehensive Bioconductor package for supervised classification with high dimensional data. BMC Bioinformatics 9: 439

See Also

evaluation


CMA documentation built on Nov. 8, 2020, 5:02 p.m.