CluMix (version 2.3.1)

dendro.variables: Variables dendrogram

Description

Get dendrogram for variables of mixed types

Usage

dendro.variables(data, method = c("associationMeasures", "distcor", "ClustOfVar"), 
  linkage="ward.D2", associationFun = association, check.psd = TRUE)

Arguments

data

data frame with variables of interest

method

If "associationMeasures", similarities between variables are assessed by combination of appropriate measures of association for different pairs of data types. If "distcor", distances between variables are calculated based on distance correlation. In both cases, then a dendrogram is derived by standard hierarchical clustering (hclust). If "ClustOfVar", variables are clustered by hclustvar from the ClustOfVar package.

linkage

agglomeration method used for hierarchical clustering when dist.variables.method = "associationMeasures"; corresponds to parameter method of hclust

associationFun

By default, appropriate association measures are chosen for each pair of variables, see association for details. But the user can also define a function that for any two variables calculates a similarity measure. Ignored if dist.variables.method = "ClustOfVar"

check.psd

If TRUE, it is checked if the variable's similarity matrix S is positive semi-definite (p.s.d.), and if not it is transformed to a p.s.d. one by nearPD, see dist.variables for details. Ignored if dist.variables.method = "ClustOfVar"

Value

An object of class dendrogram

Details

Clustering of variables can either be done i) similarity-based using measures of association, ii) similarity-based using distance correlation, or iii) by the ClustOfVar approach, which uses principal components analysis for mixed data.

References

Hummel M, Edelmann D, Kopp-Schneider A (2017). Clustering of samples and variables with mixed-type data. PLOS ONE, 12(11):e0188274.

Chavent M, Kuentz-Simonet V, Liquet B, Saracco J (2012). ClustOfVar: An R Package for the Clustering of Variables. Journal of Statistical Software, 50:1-16.

See Also

association, similarity.variables, dist.variables, dendro.subjects, mix.heatmap, hclustvar

Examples

# NOT RUN {
data(mixdata)

dend1 <- dendro.variables(mixdata, method="associationMeasures")
plot(dend1)

dend2 <- dendro.variables(mixdata, method="distcor")
plot(dend2)

dend3 <- dendro.variables(mixdata, method="ClustOfVar")
plot(dend3)
# }