com.numericalmethod.suanshu.stats.cointegration
Class CointegrationMle

java.lang.Object
  com.numericalmethod.suanshu.stats.cointegration.CointegrationMle

public class CointegrationMle
extends java.lang.Object

Two or more time series are cointegrated if they each share a common type of stochastic drift, that is, to a limited degree they share a certain type of behavior in terms of their long-term fluctuations, but they do not necessarily move together and may be otherwise unrelated.

This class implements the Johansen method to estimate the cointegrating factors.

The Johansen test, named after Søren Johansen, is a procedure for testing cointegration of several I(1) time series using MLE. This test permits more than one cointegrating relationship. It is more generally applicable than the Engle–Granger test.

See Also:

• Wikipedia: Cointegration
• Wikipedia: Johansen test
• Søren Johansen. Likelihood-Based Inference in Cointegrated Vector Autoregressive Models. Oxford University Press, USA. February 1, 1996.

Field Summary

boolean	intercept indicate whether an intercept is included in the computation
JohansenAsymptoticDistribution.Test	test the type of Johansen test

Constructor Summary

CointegrationMle(SimpleMultiVariateTimeSeries ts, boolean intercept)
Perform the Johansen procedure on a multi-variate time series.

CointegrationMle(SimpleMultiVariateTimeSeries ts, boolean intercept, int p)
Perform the Johansen procedure on a multi-variate time series, using the EIGEN test.

CointegrationMle(SimpleMultiVariateTimeSeries ts, boolean intercept, int p, Matrix D, JohansenAsymptoticDistribution.Test test)
Perform the Johansen procedure on a multi-variate time series.

Method Summary

ImmutableMatrix	alpha() Get the set of adjusting coefficients.
ImmutableMatrix	beta() Get the set of cointegrating factors.
ImmutableVector	beta(int r) Get the r-th cointegrating factor, counting from 1.
ImmutableVector	eigenvalues() Get the set of real eigenvalues.
ImmutableVector	getStats() Get the set of likelihood ratio test statistics for testing H(r) in H(r+1).

Methods inherited from class java.lang.Object

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

Field Detail

intercept

public final boolean intercept

indicate whether an intercept is included in the computation

test

public final JohansenAsymptoticDistribution.Test test

the type of Johansen test

Constructor Detail

CointegrationMle

public CointegrationMle(SimpleMultiVariateTimeSeries ts,
                        boolean intercept,
                        int p,
                        Matrix D,
                        JohansenAsymptoticDistribution.Test test)

Perform the Johansen procedure on a multi-variate time series.

Parameters:

ts - a multi-variate time series

intercept - indicate whether an intercept is included in the computation

p - the number of lags, e.g., 2

D - the exogenous factor matrix

test - the type of Johansen test

CointegrationMle

public CointegrationMle(SimpleMultiVariateTimeSeries ts,
                        boolean intercept,
                        int p)

Perform the Johansen procedure on a multi-variate time series, using the EIGEN test.

Parameters:

ts - a multi-variate time series

intercept - indicate whether an intercept is included in the computation

p - the number of lags, e.g., 2

CointegrationMle

public CointegrationMle(SimpleMultiVariateTimeSeries ts,
                        boolean intercept)

Perform the Johansen procedure on a multi-variate time series. Default number of lags = 2.

Parameters:

ts - a multi-variate time series

intercept - indicate whether an intercept is included in the computation

Method Detail

alpha

public ImmutableMatrix alpha()

Get the set of adjusting coefficients.

Returns:

α, the adjusting coefficients

beta

public ImmutableMatrix beta()

Get the set of cointegrating factors.

Returns:

β, the cointegrating factors

beta

public ImmutableVector beta(int r)

Get the r-th cointegrating factor, counting from 1.

Returns:

β, the r-th cointegrating factor

eigenvalues

public ImmutableVector eigenvalues()

Get the set of real eigenvalues.

Returns:

the real eigenvalues

getStats

public ImmutableVector getStats()

Get the set of likelihood ratio test statistics for testing H(r) in H(r+1).

Returns:

the likelihood ratio test statistics