neginc: Neg-entropy normality index for cluster validation

In fpc: Flexible Procedures for Clustering

Neg-entropy normality index for cluster validation

Description

Cluster validity index based on the neg-entropy distances of within-cluster distributions to normal distribution, see Lago-Fernandez and Corbacho (2010).

Usage

neginc(x,clustering)

Arguments

x	something that can be coerced into a numerical matrix. Euclidean dataset.
clustering	vector of integers with length =nrow(x); indicating the cluster for each observation.

Value

Index value, see Lago-Fernandez and Corbacho (2010). The lower (i.e., the more negative) the better.

Author(s)

Christian Hennig [e-mail] https://www.unibo.it/sitoweb/christian.hennig/en/

References

Lago-Fernandez, L. F. and Corbacho, F. (2010) Normality-based validation for crisp clustering. Pattern Recognition 43, 782-795.

Examples

  options(digits=3)
  iriss <- as.matrix(iris[c(1:10,51:55,101:105),-5])
  irisc <- as.numeric(iris[c(1:10,51:55,101:105),5])
  neginc(iriss,irisc)

fpc documentation built on Jan. 7, 2023, 1:13 a.m.