NAME

PDL::Filter::LinPred - Linear predictive filtering

SYNOPSIS

$a = new PDL::Filter::LinPred(
	{NLags => 10,
	 LagInterval => 2,
	 LagsBehind => 2,
	 Data => $dat});

($pd,$corrslic) = $a->predict($dat);

DESCRIPTION

A filter by doing linear prediction: tries to predict the next value in a data stream as accurately as possible. The filtered data is the predicted value. The parameters are

NLags

Number of time lags used for prediction

LagInterval

How many points each lag should be

LagsBehind

If, for some strange reason, you wish to predict not the next but the one after that (i.e. usually f(t) is predicted from f(t-1) and f(t-2) etc., but with LagsBehind => 2, f(t) is predicted from f(t-2) and f(t-3)).

Data

The input data, which may contain other dimensions past the first (time). The extraneous dimensions are assumed to represent epochs so the data is just concatenated.

AutoCovar

As an alternative to Data, you can just give the temporal autocorrelation function.

Smooth

Don't do prediction or filtering but smoothing.

The method predict gives a prediction for some data plus a corresponding slice of the data, if evaluated in list context. This slice is given so that you may, if you wish, easily plot them atop each other.

The rest of the documentation is under lazy evaluation.

AUTHOR

Copyright (C) Tuomas J. Lukka 1997. Reproducing documentation from the pdl distribution in any way that does not include a statement telling who the original authors are is forbidden. Reproducing and/or distributing the documentation in any form that alters the text is forbidden.