miss_mixmvnorm_mstep: the M step function of the EM algorithm

In hhsmm: Hidden Hybrid Markov/Semi-Markov Model Fitting

the M step function of the EM algorithm

Description

The M step function of the EM algorithm for the mixture of multivariate normals as the emission distribution with missing values using the observation matrix and the estimated weight vectors

Usage

miss_mixmvnorm_mstep(x, wt1, wt2, par)

Arguments

x	the observation matrix which can contain missing values (NA or NaN)
wt1	the state probabilities matrix (number of observations times number of states)
wt2	the mixture components probabilities list (of length nstate) of matrices (number of observations times number of mixture components)
par	the parameters of the model in the previous step of the EM algorithm. For initialization of the model when the data is initially imputed, par can be NULL

Value

list of emission (mixture multivariate normal) parameters: (mu, sigma and mix.p)

Author(s)

Morteza Amini, [e-mail]

Examples

data(CMAPSS)
n = nrow(CMAPSS$train$x)
wt1 = matrix(runif(3*n),nrow=n,ncol=3)
wt2 = list()
for(j in 1:3) wt2[[j]] = matrix(runif(5*n),nrow=n,ncol=5)
emission = miss_mixmvnorm_mstep(CMAPSS$train$x, wt1, wt2, par=NULL)

hhsmm documentation built on Aug. 8, 2023, 9:06 a.m.