hc {mclust}R Documentation

Model-based Hierarchical Clustering

Description

Agglomerative hierarchical clustering based on maximum likelihood criteria for Gaussian mixture models parameterized by eigenvalue decomposition.

Usage

hc(data,
   modelName = mclust.options("hcModelNames")[1],  
   use = mclust.options("hcUse"), ...)

Arguments

data

A numeric vector, matrix, or data frame of observations. Categorical variables are not allowed. If a matrix or data frame, rows correspond to observations and columns correspond to variables.

modelName

A character string indicating the model to be used.
Possible models are:

"E": equal variance (one-dimensional)
"V" : spherical, variable variance (one-dimensional)
"EII": spherical, equal volume
"VII": spherical, unequal volume
"EEE": ellipsoidal, equal volume, shape, and orientation
"VVV": ellipsoidal, varying volume, shape, and orientation.

By default the first model listed in mclust.options("hcModelNames"), i.e. "VVV", is used.

use

A character string specifying what type of data/transformation should be used for model-based hierarchical clustering.
This is experimental and it is only useful for the initialization of EM algorithm. By default it uses the method specified in mclust.options("hcUse"), which is set to "VARS", i.e. the original input variables.

...

Arguments for the method-specific hc functions. See for example hcE.

Details

Most models have memory usage of the order of the square of the number groups in the initial partition for fast execution. Some models, such as equal variance or "EEE", do not admit a fast algorithm under the usual agglomerative hierarchical clustering paradigm. These use less memory but are much slower to execute.

Value

A numeric two-column matrix in which the ith row gives the minimum index for observations in each of the two clusters merged at the ith stage of agglomerative hierarchical clustering.

Note

If modelName = "E" (univariate with equal variances) or modelName = "EII" (multivariate with equal spherical covariances), then the method is equivalent to Ward's method for hierarchical clustering.

References

J. D. Banfield and A. E. Raftery (1993). Model-based Gaussian and non-Gaussian Clustering. Biometrics 49:803-821.

C. Fraley (1998). Algorithms for model-based Gaussian hierarchical clustering. SIAM Journal on Scientific Computing 20:270-281.

C. Fraley and A. E. Raftery (2002). Model-based clustering, discriminant analysis, and density estimation. Journal of the American Statistical Association 97:611-631.

See Also

hcE,..., hcVVV, hclass, mclust.options

Examples

hcTree <- hc(modelName = "VVV", data = iris[,-5])
cl <- hclass(hcTree,c(2,3))

## Not run: 
par(pty = "s", mfrow = c(1,1))
clPairs(iris[,-5],cl=cl[,"2"])
clPairs(iris[,-5],cl=cl[,"3"])

par(mfrow = c(1,2))
dimens <- c(1,2)
coordProj(iris[,-5], dimens = dimens, classification=cl[,"2"])
coordProj(iris[,-5], dimens = dimens, classification=cl[,"3"])

## End(Not run)
[Package mclust version 5.4.1 Index]