ARBurgFit Routine

Summary

Burg AR estimation.

Declaration

Procedure ARBurgFit(Data: TVec; Phi: TVec; out Sigma2: TSample; StdErrs: TVec);

Parameter	Description
Data	Zero-mean time series. If this is not the case, subtract the mean from data.
Phi	Returns estimates for Phi coefficients. AR(p) order is determined by Phi length.
Sigma2	Returns Burg estimated variance for AR process.
StdErrs	Returns estimated phi coefficients standard errors.

Description

Performs Burg estimation for pure (AR) model.

See Also
ARYuleWalkerFit

Example 1

Calculate initial estimates for AR(3) process by using Burg's algorithm.

  Uses MtxExpr, StatTimeSerAnalysis, Math387;
  procedure Example;
  var ts,phi: Vector;
      s2: TSample;
  begin
    ts.LoadFromFile('timeser.vec');
    phi.Length := 3; // for AR(3) process
    ARBurgFit(ts,phi,s2);
  end;

  #include "MtxVecCpp.h"
  #include "Math387.hpp"
  #include "StatTimeSerAnalysis.hpp"
  void __fastcall Example();
  {
    Vector ts,phi;
    ts->LoadFromFile("timeser.vec");
    phi->Length = 3; // AR(3) process
    double s2;
    ARBurgFit(ts,phi,s2,NULL);
  }

  using Dew.Math;
  using Dew.Stats;
  using Dew.Stats.Units;
  namespace Dew.Examples
  {
    private void Example()
    {
      Vector ts = new Vector(0);
      Vector phi = new Vector(0);
      double s2;
      ts.LoadFromFile("timeser.vec");
      phi.Length = 3; // for AR(3) process
      StatTimeSerAnalysis.ARBurgFit(ts,phi,out s2,null);
    }
  }