# SuanShu, a Java numerical and statistical library

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

## Class MultivariateAutoCorrelationFunction

• All Implemented Interfaces:
Function<Vector,Matrix>, RntoMatrix
Direct Known Subclasses:
VARMAAutoCorrelation

public abstract class MultivariateAutoCorrelationFunction
extends R2toMatrix
This is the auto-correlation function of a multi-dimensional time series {Xt}. $Y_{i,j} = E((X_i - \mu_i) \times (X_j - \mu_j)') \\ \rho(i, j) = \frac{Y_{i,j}}{\sqrt{Y_{i,i}Y_{j,j}}}$ For a stationary process, the auto-correlation depends only on the lag, |i - j|.

• ### Nested classes/interfaces inherited from interface com.numericalmethod.suanshu.analysis.function.Function

Function.EvaluationException
• ### Constructor Summary

Constructors
Constructor and Description
MultivariateAutoCorrelationFunction()
• ### Method Summary

All Methods
Modifier and Type Method and Description
Matrix get(int i, int j)
Get the auto-correlation of Xi and Xj.
• ### Methods inherited from class com.numericalmethod.suanshu.analysis.function.matrix.R2toMatrix

dimensionOfDomain, dimensionOfRange, evaluate, evaluate
• ### Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
• ### Constructor Detail

• #### MultivariateAutoCorrelationFunction

public MultivariateAutoCorrelationFunction()
• ### Method Detail

• #### get

public Matrix get(int i,
int j)
Get the auto-correlation of Xi and Xj.
Parameters:
i - i > 0
j - j > 0
Returns:
the auto-correlation Matrix indexed by [i, j]