com.numericalmethod.suanshu.stats.timeseries.linear.multivariate.stationaryprocess.arma

Class ARMAModel

java.lang.Object

com.numericalmethod.suanshu.stats.timeseries.linear.multivariate.arima.ARIMAXModel

com.numericalmethod.suanshu.stats.timeseries.linear.multivariate.arima.ARIMAModel

com.numericalmethod.suanshu.stats.timeseries.linear.multivariate.stationaryprocess.arma.ARMAModel

All Implemented Interfaces:

java.io.Serializable

Direct Known Subclasses:

ARModel, MAModel

public class ARMAModel
extends ARIMAModel

This class represents a multivariate ARMA model.

See Also:

"P. J. Brockwell and R. A. Davis, Time Series: Theory and Methods, Springer, 2006.", Serialized Form

Field Summary

Fields inherited from class com.numericalmethod.suanshu.stats.timeseries.linear.multivariate.arima.ARIMAXModel

mu, phi, psi, sigma, theta

Constructor Summary

Constructors

Constructor and Description
ARMAModel(ARMAModel that) Copy constructor.
ARMAModel(ARMAModel model) Cast a univariate ARMA model to a multivariate model.
ARMAModel(Matrix[] phi, Matrix[] theta) Construct a zero-intercept (mu) multivariate ARMA model with unit variance.
ARMAModel(Matrix[] phi, Matrix[] theta, Matrix sigma) Construct a zero-intercept (mu) multivariate ARMA model.
ARMAModel(Vector mu, Matrix[] phi, Matrix[] theta) Construct a multivariate ARMA model with unit variance.
ARMAModel(Vector mu, Matrix[] phi, Matrix[] theta, Matrix sigma) Construct a multivariate ARMA model.

Method Summary

Modifier and Type	Method and Description
Matrix	armaMean(Matrix arLags, Matrix maLags) Compute the multivariate ARMA conditional mean.
Matrix	armaMeanNoIntercept(Matrix arLags, Matrix maLags) Compute the zero-intercept (mu) multivariate ARMA conditional mean.

Methods inherited from class com.numericalmethod.suanshu.stats.timeseries.linear.multivariate.arima.ARIMAModel

getArma

Methods inherited from class com.numericalmethod.suanshu.stats.timeseries.linear.multivariate.arima.ARIMAXModel

AR, AR, d, dimension, getArmax, MA, MA, maxPQ, mu, p, psi, q, sigma

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

ARMAModel

public ARMAModel(Vector mu,
                 Matrix[] phi,
                 Matrix[] theta,
                 Matrix sigma)

Construct a multivariate ARMA model.

Parameters:

mu - the intercept (constant) vector

phi - the AR coefficients (excluding the initial 1); null if no AR coefficient

theta - the MA coefficients (excluding the initial 1); null if no MA coefficient

sigma - the covariance matrix of white noise

ARMAModel

public ARMAModel(Vector mu,
                 Matrix[] phi,
                 Matrix[] theta)

Construct a multivariate ARMA model with unit variance.

Parameters:

mu - the intercept (constant) vector

phi - the AR coefficients (excluding the initial 1); null if no AR coefficient

theta - the MA coefficients (excluding the initial 1); null if no MA coefficient

ARMAModel

public ARMAModel(Matrix[] phi,
                 Matrix[] theta,
                 Matrix sigma)

Construct a zero-intercept (mu) multivariate ARMA model.

Parameters:

phi - the AR coefficients (excluding the initial 1); null if no AR coefficient

theta - the MA coefficients (excluding the initial 1); null if no MA coefficient

sigma - the covariance matrix of white noise

ARMAModel

public ARMAModel(Matrix[] phi,
                 Matrix[] theta)

Construct a zero-intercept (mu) multivariate ARMA model with unit variance.

Parameters:

phi - the AR coefficients (excluding the initial 1); null if no AR coefficient

theta - the MA coefficients (excluding the initial 1); null if no MA coefficient

ARMAModel

public ARMAModel(ARMAModel that)

Copy constructor.

Parameters:

that - a multivariate ARMA model

ARMAModel

public ARMAModel(ARMAModel model)

Cast a univariate ARMA model to a multivariate model.

Parameters:

model - a univariate ARMA model

Method Detail

armaMeanNoIntercept

public Matrix armaMeanNoIntercept(Matrix arLags,
                                  Matrix maLags)

Compute the zero-intercept (mu) multivariate ARMA conditional mean.

Parameters:

arLags - the AR lags

maLags - the MA lags

Returns:

the conditional mean

armaMean

public Matrix armaMean(Matrix arLags,
                       Matrix maLags)

Compute the multivariate ARMA conditional mean.

Parameters:

arLags - the AR lags

maLags - the MA lags

Returns:

the conditional mean