similarity.subjects: Similarity matrix for subjects

In CluMix: Clustering and Visualization of Mixed-Type Data

Description

Get similarity matrix for subjects (observations) based on variables of mixed data types

Usage

similarity.subjects(data, weights)

Arguments

data	data frame
weights	optional vector of weights for variables in data

Details

Distances d.ij between subjects are calculated based on Gower's general similarity coefficient with an extension of Podani for ordinal variables, see gowdis. In the case that all variables are quantitative, Euclidean distances are used. Similarities s.ij are calculated as s.ij = 1 - d.ij.

Value

Matrix of similarity values for each pair of subjects

Author(s)

Manuela Hummel

References

Gower J (1971). A general coefficient of similarity and some of its properties. Biometrics, 27:857-871.

Podani J (1999). Extending Gower's general coefficient of similarity to ordinal characters. Taxon, 48(2):331-340.

See Also

dendro.subjects, dist.subjects, mix.heatmap

Examples

data(mixdata)

S <- similarity.subjects(mixdata)

## example with weights
w <- rep(1:2, each=5)
S <- similarity.subjects(mixdata, weights=w)

CluMix documentation built on Jan. 21, 2019, 5:05 p.m.