com.numericalmethod.suanshu.signalprocessing
Class Innovations

java.lang.Object
  com.numericalmethod.suanshu.signalprocessing.Innovations

public class Innovations
extends java.lang.Object

An innovation is the difference between the observed value of a variable at time t and the optimal forecast of that value based on information available prior to time t.

If the forecasting method is working correctly successive innovations are uncorrelated with each other, i.e., constitute a white noise time series. Thus it can be said that the innovation time series is obtained from the measurement time series by a process of 'whitening', or removing the predictable component.

See Also:

Wikipedia: Innovations (signal processing)

Constructor Summary

Innovations(double[] innovations)
Construct an Innovations from an array of innovations.

Innovations(Innovations innovation)
Construct a new Innovations from another one.

Innovations(int length)
Construct an innovation series from the standard Normal distribution.

Innovations(int length, double mu, double var)
Construct an innovation series from a Normal distribution.

Innovations(int length, double mu, double var, int seed)
Construct an innovation series from a Normal distribution.

Innovations(int length, RandomNumberGenerator rng)
Construct an Innovations from a random number generator.

Innovations(int length, RandomNumberGenerator rng, int seed)
Construct an Innovations from a random number generator.

Innovations(int length, UnivariateDistribution dist)
Construct an Innovations from a distribution.

Innovations(int length, UnivariateDistribution dist, double mu, double var)
Construct an Innovations from a distribution.

Innovations(int length, UnivariateDistribution dist, double mu, double var, long seed)
Construct an Innovations from a distribution.

Method Summary

double[]	toArray() Get a copy of the innovations.
double[]	toArray(int length) Get a copy of the (truncated) innovations.

Methods inherited from class java.lang.Object

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

Constructor Detail

Innovations

public Innovations(double[] innovations)

Construct an Innovations from an array of innovations.

Parameters:

innovations - an array of innovations

Innovations

public Innovations(Innovations innovation)

Construct a new Innovations from another one.

Parameters:

innovation - an Innovations

Innovations

public Innovations(int length,
                   UnivariateDistribution dist,
                   double mu,
                   double var,
                   long seed)

Construct an Innovations from a distribution.

Parameters:

length - the length of the innovations

dist - the distribution

mu - the mean shift of the distribution

var - the variance scale of the distribution

seed - the seed

Innovations

public Innovations(int length,
                   UnivariateDistribution dist,
                   double mu,
                   double var)

Construct an Innovations from a distribution.

Parameters:

length - the length of the innovations

dist - the distribution

mu - the mean shift of the distribution

var - the variance scale of the distribution

Innovations

public Innovations(int length,
                   UnivariateDistribution dist)

Construct an Innovations from a distribution.

Parameters:

length - the length of the innovations

dist - the distribution

Innovations

public Innovations(int length,
                   RandomNumberGenerator rng,
                   int seed)

Construct an Innovations from a random number generator.

Parameters:

length - the length of the innovations

rng - a random number generator

seed - the seed

Innovations

public Innovations(int length,
                   RandomNumberGenerator rng)

Construct an Innovations from a random number generator.

Parameters:

length - the length of the innovations

rng - a random number generator

Innovations

public Innovations(int length,
                   double mu,
                   double var,
                   int seed)

Construct an innovation series from a Normal distribution.

Parameters:

length - the length of the innovations

mu - the mean of the distribution

var - the variance of the distribution

seed - the seed

Innovations

public Innovations(int length,
                   double mu,
                   double var)

Construct an innovation series from a Normal distribution.

Parameters:

length - the length of the innovations

mu - the mean of the distribution

var - the variance of the distribution

Innovations

public Innovations(int length)

Construct an innovation series from the standard Normal distribution.

Parameters:

length - the length of the innovations

Method Detail

toArray

public double[] toArray(int length)

Get a copy of the (truncated) innovations.

We return only the head elements of the length specified.

Parameters:

length - the length of the time series of innovations

Returns:

a copy of the (truncated) innovations

toArray

public double[] toArray()

Get a copy of the innovations.

Returns:

a copy of the innovations