40_lmt: Likelihood Mixture Tests

In EMCluster: EM Algorithm for Model-Based Clustering of Finite Mixture Gaussian Distribution

Likelihood Mixture Tests

Description

This function test two mixture Gaussian models with unstructured covariance matrix and different numbers of clusters.

Usage

lmt(emobj.0, emobj.a, x, tau = 0.5, n.mc.E.delta = 1000,
    n.mc.E.chi2, verbose = FALSE)

Arguments

emobj.0	a emret object for the null hypothesis.
emobj.a	a emret object for the alternative hypothesis.
x	the data matrix, dimension n * p.
tau	proportion of null and alternative hypotheses.
n.mc.E.delta	number of Monte Carlo simulations for expectation of delta (difference of logL).
n.mc.E.chi2	number of Monte Carlo simulations for expectation of chisquare statistics.
verbose	if verbose.

Details

This function calls several subroutines to compute information, likelihood ratio statistics, degrees of freedom, non-centrality of chi-squared distributions ... etc. Based on Monte Carlo methods to estimate parameters of likelihood mixture tests, this function return a p-value for testing H0: emobj.0 v.s. Ha: emobj.a.

Value

A list of class lmt are returned.

Author(s)

Wei-Chen Chen [e-mail] and Ranjan Maitra.

References

https://www.stat.iastate.edu/people/ranjan-maitra

See Also

init.EM.

Examples

## Not run: 
library(EMCluster, quietly = TRUE)
set.seed(1234)

x <- as.matrix(iris[, 1:4])
p <- ncol(x)
min.n <- p * (p + 1) / 2
.EMC$short.iter <- 200

ret.2 <- init.EM(x, nclass = 2, min.n = min.n, method = "Rnd.EM")
ret.3 <- init.EM(x, nclass = 3, min.n = min.n, method = "Rnd.EM")
ret.4 <- init.EM(x, nclass = 4, min.n = min.n, method = "Rnd.EM")

(lmt.23 <- lmt(ret.2, ret.3, x))
(lmt.34 <- lmt(ret.3, ret.4, x))
(lmt.24 <- lmt(ret.2, ret.4, x))

## End(Not run)

EMCluster documentation built on Aug. 20, 2022, 5:05 p.m.