datan

Class LsqMar

java.lang.Object

datan.LsqMar

public final class LsqMar
extends java.lang.Object

A class performing the least-squares fit of a nonlinear function to a set of data,using Marquardt's method.

Author:

Siegmund Brandt.

Constructor Summary

Constructors

Constructor and Description
LsqMar(DatanVector t, DatanVector y, DatanVector deltay, DatanVector x, int[] list, DatanUserFunction luf)

Method Summary

Methods

Modifier and Type	Method and Description
double	getChiSquare()
DatanMatrix	getCovarianceMatrix()
DatanVector	getResult()
boolean	hasConverged()

Methods inherited from class java.lang.Object

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

Constructor Detail

LsqMar

public LsqMar(DatanVector t,
      DatanVector y,
      DatanVector deltay,
      DatanVector x,
      int[] list,
      DatanUserFunction luf)

Parameters:

t - vector, the elements of which are the controlled variables t_i

y - vector of the corresponding measured values.

deltay - vector of measurement errors.

x - vector of first approximations of unknowns.

list - array containing the elements of a list specifying which of the n variables are fixed (list element = 0) and which are adjustable (list element = 1).

luf - user function which must be an extension of the abstract class DatanUserFunction.

Method Detail

getResult

public DatanVector getResult()

Returns:

the vector of unknowns..

getCovarianceMatrix

public DatanMatrix getCovarianceMatrix()

Returns:

the covariance matrix ot the unknowns.

getChiSquare

public double getChiSquare()

Returns:

the value of the minimum function.

hasConverged

public boolean hasConverged()

Returns:

true if iteration successful, false otherwise.