pal.statistics
Class KishinoHasegawaTest

java.lang.Object
  pal.statistics.KishinoHasegawaTest

All Implemented Interfaces:

Report

public class KishinoHasegawaTest
extends java.lang.Object
implements Report

Kishino-Hasegawa-(Templeton)-Test (1989, 1983) to compare a set of evolutionary hypotheses

Version:

$Id: KishinoHasegawaTest.java,v 1.6 2004/02/25 02:55:55 matt Exp $

Author:

Korbinian Strimmer

Field Summary

int	bestH number of maximum likelihood hypothesis
double[]	delta log-likelihood difference to maximum likelihood hypothesis
double[]	deltaSE estimated error of log-likelihood differences
double[]	pval corresponding p-value (two-sided test on normal distribution)

Constructor Summary

KishinoHasegawaTest()

Method Summary

void	compare(double[][] sLogL) Compare all given hypotheses to the best (ML) hypothesis and store results in public arrays delta, deltaSE, pval (which will automatically be created by this procedure).
void	compare(double[][] pLogL, int[] alias) Compare all given hypotheses to the best (ML) hypothesis and store results in public arrays delta, deltaSE, pval (which will automatically be created by this procedure).
void	report(java.io.PrintWriter out) print human readable report (e.g., on parameters and associated model)

Methods inherited from class java.lang.Object

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

Field Detail

bestH

public int bestH

number of maximum likelihood hypothesis

delta

public double[] delta

log-likelihood difference to maximum likelihood hypothesis

deltaSE

public double[] deltaSE

estimated error of log-likelihood differences

pval

public double[] pval

corresponding p-value (two-sided test on normal distribution)

Constructor Detail

KishinoHasegawaTest

public KishinoHasegawaTest()

Method Detail

compare

public void compare(double[][] sLogL)

Compare all given hypotheses to the best (ML) hypothesis and store results in public arrays delta, deltaSE, pval (which will automatically be created by this procedure).

Parameters:

sLogL - log-likelihoods of each site

compare

public void compare(double[][] pLogL,
                    int[] alias)

Compare all given hypotheses to the best (ML) hypothesis and store results in public arrays delta, deltaSE, pval (which will automatically be created by this procedure).

Parameters:

pLogL - log-likelihoods of each pattern

alias - map of patterns to sites in sequence

report

public void report(java.io.PrintWriter out)

Description copied from interface: Report

print human readable report (e.g., on parameters and associated model)

Specified by:

report in interface Report

Parameters:

out - output stream