com.numericalmethod.suanshu.stats.dlm
Class LinearKalmanFilter

java.lang.Object
  com.numericalmethod.suanshu.stats.dlm.LinearKalmanFilter

public class LinearKalmanFilter
extends java.lang.Object

Constructor Summary

LinearKalmanFilter(Dlm model)

Method Summary

void	filtering(MultiVariateTimeSeries Yt) Filter the observations without control variable.
void	filtering(MultiVariateTimeSeries Yt, MultiVariateTimeSeries Ut) Filter the observations.
SimpleMultiVariateTimeSeries	getFittedStates() Get the posterior expected states.
SimpleMultiVariateTimeSeries	getPredictedObservations() Get the a prior observation predictions.

Methods inherited from class java.lang.Object

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

Constructor Detail

LinearKalmanFilter

public LinearKalmanFilter(Dlm model)

Method Detail

filtering

public void filtering(MultiVariateTimeSeries Yt,
                      MultiVariateTimeSeries Ut)

Filter the observations.

Parameters:

Yt - the observations

Ut - the controls

filtering

public void filtering(MultiVariateTimeSeries Yt)

Filter the observations without control variable.

Parameters:

Yt - the observations

getFittedStates

public SimpleMultiVariateTimeSeries getFittedStates()

Get the posterior expected states.

Returns:

the fitted states

getPredictedObservations

public SimpleMultiVariateTimeSeries getPredictedObservations()

Get the a prior observation predictions.

Returns:

the predicted observations