LD: Levinson Durbin algorithm

In hlennon/copulaIVTS: Dependence modelling of a digitised Gaussian ARMA(p,q) copula model for Integer-Valued Time Series

Description

Levinson Dubin Algorithm, following Brockwell & Davis 1987, to compute phi_k's and arrange in phi.mat Also computes phi_kk's and tau's needed for likelihood.

Usage

LD(r, n-1)

Arguments

r	a vector of autocovariances
n	a numeric to specify the length of vector taus/dimension of matrix phi_kks

Details

See Brockwell and Davis

Value

phi.mat	A n x n matrix of phi_kk's
s	a vector of tau's, of length n

Author(s)

Hannah Lennon

References

Brockwell and Davis (1987)

Examples

r      <- as.numeric(ARMAacf(ar=0.7, ma=-0.5, lag.max=10, pacf=FALSE))   
n      <- 5 
output <- LD(r, n-1)

PHI    <- t(output[, 1:n])    # matrix of n x n 
tau    <- output[,(n+1)]      # vector of n
PHI; tau
            

hlennon/copulaIVTS documentation built on Dec. 20, 2021, 4:45 p.m.