ShortenFilter Routine

Summary

Memory-shortening filter.

Declaration

Procedure ShortenFilter(Data: TVec; S: TVec; out tau: Integer; Filter: TVec = nil; MaxTau: Integer = 15);

Parameter	Description
Data	Original time series.
S	Returns transformed time series.
tau	Returns optimal tau shortening index.
Filter	If set, it returns coefficients of memory shortening filter. Size of Phi is adjusted automatically.
MaxTau	Maximum number of iterations in ERR minimization (default value 15).

Description

Decide if time series is "long-memory", and if so, apply a memory-shortening transformation, as defined in Brockwell, page 318.

See Also
ARARFit
ARARForecast

Example 1

Shorten time series and retrieve optimal tau lag and shortening filter polynomial coefficients.

  Uses MtxExpr, StatTimeSerAnalysis;
  var ts,s,phi: Vector;
    tau: Integer;
  begin
    ts.LoadFromFile('Deaths.vec');
    ShortenFilter(ts,s,tau,phi);
  end;

  #include "MtxVecCpp.h"
  #include "Math387.hpp"
  #include "StatTimeSerAnalysis.hpp"
  void __fastcall Example();
  {
    Vector ts,s,phi;
    int tau;
    ts->LoadFromFile("Deaths.vec");
    ShortenFilter(ts,s,tau,phi);
  }

  using Dew.Math;
  using Dew.Stats;
  using Dew.Stats.Units;
  namespace Dew.Examples
  {
    private void Example()
    {
      Vector ts = new Vector(0);
      Vector s = new Vector(0);
      Vector phi = new Vector(0);
      int tau;
      ts.LoadFromFile("Deaths.vec");
      StatTimeSerAnalysis.ShortenFilter(ts,s,out tau,phi,15);
    }
  }