Categories &

Functions List

Class Definition: CalinskiHarabaszEvaluation

statistics: obj = evalclusters (x, clust, CalinskiHarabasz)
statistics: obj = evalclusters (…, Name, Value)

A Calinski-Harabasz object to evaluate clustering solutions.

A CalinskiHarabaszEvaluation object is a ClusterCriterion object used to evaluate clustering solutions using the Calinski-Harabasz criterion.

The Calinski-Harabasz index is based on the ratio between SSb and SSw. SSb is the overall variance between clusters, that is the variance of the distances between the centroids. SSw is the overall variance within clusters, that is the sum of the variances of the distances between each datapoint and its centroid.

The best solution according to the Calinski-Harabasz criterion is the one that scores the highest value.

See also: evalclusters, ClusterCriterion, DaviesBouldinEvaluation, GapEvaluation, SilhouetteEvaluation

Source Code: CalinskiHarabaszEvaluation

Method: addK

CalinskiHarabaszEvaluation: obj = addK (obj, K)

Add a new cluster array to inspect the CalinskiHarabaszEvaluation object.

Method: compact

CalinskiHarabaszEvaluation: obj = compact (obj)

Return a compact CalinskiHarabaszEvaluation object (not implemented yet).

Method: plot

CalinskiHarabaszEvaluation: plot (obj)
CalinskiHarabaszEvaluation: h = plot (obj)

Plot the evaluation results.

Plot the CriterionValues against InspectedK from the CalinskiHarabaszEvaluation, obj, to the current plot. It can also return a handle to the current plot.