VARMA_auto: computes autocovariances of VARMA

In jlivsey/sigex: Ecce Signum: Multivariate Signal Extraction

computes autocovariances of VARMA

Description

Background: function computes autocovariances of VARMA (p,q) from lag zero to maxlag, with array inputs phi and theta. VARMA equation: (1 - phi[1]B ... - phi[p]B^p) X_t = (1 + theta[1]B ...+ theta[q]B^q) WN_t

Usage

VARMA_auto(param, p, q, maxlag)

Arguments

p	- AR order
q	- MA order
maxlag	- final lag of autocovariance needed
param:	matrix of dimension m x (p+q+1)m, equals [ phi | theta | sigma ] phi: block matrix of dimension m x mp of VAR coefficients theta: block matrix of dimension m x mq of VMA coefficients sigma: m x m covariance matrix of white noise

Value

autocovariances at lags 0 through maxlag, as array of dimension m x m x (maxlag+1)

jlivsey/sigex documentation built on March 20, 2024, 3:17 a.m.