Package jphase.fit

Provides capabilities for fitting Phase type distribution parameters from data.

See:
Description

Interface Summary

PhaseFitter

This class defines the behaviour that any class for fitting data to a Phase-Type distribution should have

Class Summary

ContPhaseFitter	This class defines the behaviour that any class for fitting data to a Continuous Phase-Type distribution should have
DiscPhaseFitter	This class defines the behaviour that any class for fitting data to a Discrete Phase-Type distribution should have
EMHyperErlangFit	This class implements the Maximum Likelihood method proposed by Th�mmler, Buchholz and Telek in "A novel approach for fitting probability distributions to real trace data with the EM algorithm", 2005.
EMHyperExpoFit	This class implements the Maximum Likelihood method proposed by Khayari, Sadre and Haverkort in "Fitting world-wide web request traces with the EM algorithm", 2003.
EMPhaseFit	This class implements the Maximum Likelihood method proposed by Asmussen, Nerman and Olsson in "Fitting Phase-type Distributions via the EM algorithm", 1996.
FitterUtils	This class contains a set of methods to make some usual calculations for the PhaseFitter classes
MLContPhaseFitter	This class defines the behaviour for a class that implements a maximum likelihood algorithm for fitting data to a Continuous Phase-Type distribution
MLDiscPhaseFitter	This class defines the behaviour for a class that implements a maximum likelihood algorithm for fitting data to a Discrete Phase-Type distribution
MomentsACPH2Fit	This class implements the Matching Moments method proposed by Telek and Heindl in "Matching Moments for Acyclic discrete and continuous Phase-Type distributions of Second order", 2002.
MomentsACPHFit	* This class implements the Matching Moments method proposed by Bobbio, Horvath and Telek in "Matching threee moments with minimal acyclic Phase-Type distributions", 2005.
MomentsADPH2Fit	This class implements the Matching Moments method proposed by Telek and Heindl in "Matching Moments for Acyclic discrete and continuous Phase-Type distributions of Second order", 2002.
MomentsContPhaseFitter	This class defines the behaviour for a class that implements a moment matching algorithm for fitting data to a Continuous Phase-Type distribution
MomentsDiscPhaseFitter	This class defines the behaviour for a class that implements a moment matching algorithm for fitting data to a Discrete Phase-Type distribution
MomentsECCompleteFit	This class implements the Matching Moments method proposed by Osogami and Harchol in "Closed form solutions for mapping general distributions to quasi-minimal PH distributions", 2005.
MomentsECPositiveFit	This class implements the Matching Moments method proposed by Osogami and Harchol in "Closed form solutions for mapping general distributions to quasi-minimal PH distributions", 2005.

Package jphase.fit Description

Provides capabilities for fitting Phase type distribution parameters from data. There exists very diferent algorithms to adjust the parameters of these distributions, which can be divided in two groups: moments based methods and maximum likelihood approaches. This package includes the implementation of some of these algorithms, a framework and a set of utilities for implement new methods. For overviews, tutorials, examples, guides, and tool documentation, please see:

Copa Group WEB page.