comp_test {gcExplorer}R Documentation

Compare Cluster Results

Description

Cluster validation by testing the validity of a cluster solution under different experimental conditions.

Usage

comp_test(data, cll, N = 500, ...)

Arguments

data Dataset with the same number of rows as the clustered dataset.
cll Vector of cluster memberships of the clustered dataset.
N Number of permutations.
... Further arguments can be passed to the subfunctions.

Value

A matrix giving for each cluster the size of the cluster, the observed average within cluster distance to the computed cluster center in the new dataset, the proportion of permutations where the observed within cluster distance is lower than the permuted and the proportion of permutations where the observed within cluster distance is larger than the permuted.

Author(s)

Theresa Scharl

Examples

data(comp19)
set.seed(1111)
cl3 <- qtclust(comp19,radius=1.5,family=kccaFamily(dist=distEuclidean,
   cent=colMeans),save.data=TRUE,control=list(min.size=5))
cl3

ct1 <- comp_test(comp17, clusters(cl3), N=1000)
ct1

[Package gcExplorer version 0.9-1 Index]