EMAlgo {MixThres}R Documentation

EM algorithm

Description

EM algorithm to estimate the parameters of the mixture model.

Usage

EMAlgo(mdata, param, stop.crit)

Arguments

mdata A vector of numeric.
param A vector of parameters.
stop.crit The stopping relative precision limit for stopping EM algorithm.

Details

The traditionnal EM algorithm of Depster et al. is modified in order to correct the mean and variance biaises du to the truncatures by including a fixed-point algorithm in the M-step. Then the vector epsilon algorithm is used to accelerate the convergence of the EM algorithm.

Value

A list of result of the logLike function and a matrix of the posterior probabilities of belonging to each component of the mixture for each probe.

Author(s)

J. Aubert

References

Picard et al., Using mixture models to define a hybridization threshold in DNA microarray experiments.

Kuroda M., Sakakihara M., (2006), Accelerating the convergence of the EM algorithm using the vector epsilon algorithm, Computational Statistics & Data Analysis 51.

See Also

hybridization


[Package MixThres version 1.0 Index]