baseCode.math.metaanalysis
Class MeanDifferenceMetaAnalysis

java.lang.Object
  baseCode.math.metaanalysis.MetaAnalysis
      baseCode.math.metaanalysis.MeanDifferenceMetaAnalysis

public class MeanDifferenceMetaAnalysis

extends MetaAnalysis

Meta-analysis methods from chapter 18 of Cooper and Hedges, sections 2.1 and 3.1

These methods use the standardized mean difference statistic d:

 d_i = ( X_i ˆ t - X_i ˆ c ) / s_i
 

where X _i ^t is the mean of the treatment group in the ith study, X _i ^ct is the mean of the control group in the treatment group in the ith study, and s _i is the pooled standard deviation of the two groups. Essentially this is a t statistic.

Copyright (c) 2004 Columbia University

Version:

$Id: MeanDifferenceMetaAnalysis.java,v 1.1 2005/01/04 00:32:27 pavlidis Exp $

Author:

pavlidis

Constructor Summary

MeanDifferenceMetaAnalysis(boolean fixed)

Method Summary

double	getBsv()
double	getE()
double	getN()
double	getP()
double	getQ()
double	getV()
double	getZ()
double	run(cern.colt.list.DoubleArrayList effects, cern.colt.list.DoubleArrayList cvar)
double	run(cern.colt.list.DoubleArrayList effects, cern.colt.list.DoubleArrayList controlSizes, cern.colt.list.DoubleArrayList testSizes)
double	samplingVariance(double d, double nC, double nT) CH eqn 18-7
cern.colt.list.DoubleArrayList	samplingVariances(cern.colt.list.DoubleArrayList effects, cern.colt.list.DoubleArrayList controlSizes, cern.colt.list.DoubleArrayList testSizes) Run eqn 18-7 on a set of effect sizes.

Methods inherited from class baseCode.math.metaanalysis.MetaAnalysis

fisherCombineLogPvalues, fisherCombinePvalues, metaFEWeights, metaRESampleVariance, metaREVariance, metaREWeights, metaVariance, metaVariance, metaZscore, qStatistic, qTest, weightedMean, weightedMean

Methods inherited from class java.lang.Object

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

Constructor Detail

MeanDifferenceMetaAnalysis

public MeanDifferenceMetaAnalysis(boolean fixed)

Method Detail

run

public double run(cern.colt.list.DoubleArrayList effects,
                  cern.colt.list.DoubleArrayList controlSizes,
                  cern.colt.list.DoubleArrayList testSizes)

run

public double run(cern.colt.list.DoubleArrayList effects,
                  cern.colt.list.DoubleArrayList cvar)

Parameters:

effects -

cvar - Conditional variances.

Returns:

samplingVariance

public double samplingVariance(double d,
                               double nC,
                               double nT)

CH eqn 18-7

Parameters:

d - effect size

nC - number of samples in control group

nT - number of samples in test group

Returns:

samplingVariances

public cern.colt.list.DoubleArrayList samplingVariances(cern.colt.list.DoubleArrayList effects,
                                                        cern.colt.list.DoubleArrayList controlSizes,
                                                        cern.colt.list.DoubleArrayList testSizes)

Run eqn 18-7 on a set of effect sizes.

Parameters:

effects -

controlSizes -

testSizes -

Returns:

getP

public double getP()

getQ

public double getQ()

getZ

public double getZ()

getE

public double getE()

getV

public double getV()

getN

public double getN()

getBsv

public double getBsv()