SAGx (version 1.46.0)

gap: GAP statistic clustering figure of merit

Description

Calculates a goodness of clustering measure based on the average dispersion compared to a reference distribution.

Usage

gap(data = swiss,class = g, B = 500, cluster.func = myclus)

Arguments

data

The data matrix, with samples (observations) in rows and genes (variables)in columns

class

a vector descibing the cluster memberships of the rows of data

B

the number of bootstrap samples

cluster.func

a function taking the arguments data and k (number of clusters) and outputs cluster assignments as list elements cluster ( accessed by object$cluster ).

Value

• The GAP statistic and the standard deviation

References

Tishirani, R., Walther, G. and Hastie, T. (2000) Estimating the number of clusters in a dataset via the Gap statistic. Technical Report Stanford

Examples

library("MASS")
data(swiss)
cl <- myclus(data = swiss, k = 3)
gap(swiss,cl$cluster)