VarianceRacfAR: Covariance Matrix Residual Autocorrelations for AR

Description Usage Arguments Details Value Note Author(s) References See Also Examples

Description

Computes the variance-covariance matrix for the residual autocorrelations in an AR(p).

Usage

1
VarianceRacfAR(phi, MaxLag, n)

Arguments

phi

vector of AR coefficients

MaxLag

covariance matrix for residual autocorrelations at lags 1 ,..., m, where m = MaxLag is computes

n

length of time series

Details

The covariance matrix for the residual autocorrelations is derived in McLeod (1978, eqn. 15) for the general ARMA case. With this function one can obtain the standard deviations of the residual autocorrelations which can be used for diagnostic checking with RacfPlot.

Value

The m-by-m covariance matrix of residual autocorrelations at lags 1, ..., m, where m = MaxLag.

Note

The derivation assumes normality of the innovations, mle estimation of the parameters and a known mean-zero time series. It is easily seen that the same result still holds for IID innovations with mean zero and finite variance, any first-order efficient estimates of the parameters including the AR coefficients and mean.

Author(s)

A.I. McLeod

References

McLeod, A.I. (1978), On the distribution and applications of residual autocorrelations in Box-Jenkins modelling, Journal of the Royal Statistical Society B, 40, 296–302

See Also

VarianceRacfARp, VarianceRacfARz, RacfPlot

Examples

1
VarianceRacfAR(0.5,5,100)

FitAR documentation built on May 2, 2019, 3:22 a.m.