ecmnobj

Multivariate normal negative log-likelihood function

Syntax

Objective = ecmnobj(Data,Mean,Covariance,CholCovariance)

Arguments

Data	NUMSAMPLES-by-NUMSERIES matrix of observed multivariate normal data
Mean	NUMSERIES-by-1 column vector with mean estimate of Data
Covariance	NUMSERIES-by-NUMSERIES matrix with covariance estimate of Data
CholCovariance	(Optional) Cholesky decomposition of covariance matrix: chol(Covariance)

Description

Objective = ecmnobj(Data,Mean,Covariance,CholCovariance) computes the value of the observed negative log-likelihood function over the data given current estimates for the mean and covariance of the data.

The data matrix has NaNs for missing observations. The inputs Mean and Covariance are current estimates for model parameters.

This routine expects the Cholesky decomposition of the covariance matrix as an input. The routine computes the Cholesky decomposition if you do not explicitly specify it.