stats_clusters: Descriptive statistics for the clusters identified by the...

In QuadratiK: Collection of Methods Constructed using Kernel-Based Quadratic Distances

Descriptive statistics for the clusters identified by the Poisson kernel-based clustering.

Description

Method for objects of class pkbc which computes some descriptive for each variable with respect to the detected groups.

Method for objects of class pkbc which computes descriptive statistics for each variable with respect to the detected groups.

Usage

stats_clusters(object, ...)

## S4 method for signature 'pkbc'
stats_clusters(object, k)

Arguments

object	Object of class pkbc.
...	possible additional inputs
k	Number of clusters to be used.

Details

The function computes mean, standard deviation, median, inter-quantile range, minimum and maximum for each variable in the data set given the final membership assigned by the clustering algorithm.

Value

List with computed descriptive statistics for each dimension.

See Also

pkbc() for the clustering algorithm
pkbc for the class object definition.

Examples

#We generate three samples of 100 observations from 3-dimensional
#Poisson kernel-based densities with rho=0.8 and different mean directions
dat<-matrix(rnorm(300),ncol=3)

#Perform the clustering algorithm
pkbc_res<- pkbc(dat, 3)
stats_clusters(pkbc_res, 3)

QuadratiK documentation built on Oct. 29, 2024, 5:08 p.m.