rtkpp (version 0.8.5)

clusterDiagGaussianNames: Build a vector of Gaussian model names.

Description

In a diagonal Gaussian model, we assume that the variance matrices are diagonal in each cluster. This gives rise to 8 models:

1. The proportions can be equal or free.

The standard deviations can be equal or free for all the variables. The standard deviations can be equal or free for all the clusters.

Usage

clusterDiagGaussianNames(prop = "all", sdInCluster = "all",
  sdBetweenCluster = "all")
clusterValidDiagGaussianNames(names)

Arguments

prop

A character string equal to "equal", "free" or "all". Default is "all".

sdInCluster

A character string equal to "equal", "free" or "all". Default is "all".

sdBetweenCluster

A character string equal to "equal", "free" or "all". Default is "all".

names

a vector of character

Value

• A vector of character with the model names.

Details

The model names are summarized in the following array: llll{ Model Name Proportions s.d. in variables s.d. in clusters gaussian_p_sjk Equal Free Free gaussian_p_sj Equal Free Equal gaussian_p_sk Equal Equal Free gaussian_p_s Equal Equal Equal gaussian_pk_sjk Free Free Free gaussian_pk_sj Free Free Equal gaussian_pk_sk Free Equal Free gaussian_pk_s Free Equal Equal }

Examples

clusterDiagGaussianNames()
## same as c("gaussian_p_sk", "gaussian_pk_sk")
clusterDiagGaussianNames(prop="all", sdInCluster="equal", sdBetweenCluster= "free")