calhoun.analysis.crf.statistics
Class PredictedActualBinaryContingencyTable

java.lang.Object
  calhoun.analysis.crf.statistics.PredictedActualBinaryContingencyTable

All Implemented Interfaces:

java.io.Serializable

public class PredictedActualBinaryContingencyTable
extends java.lang.Object
implements java.io.Serializable

See Also:

Serialized Form

Constructor Summary

PredictedActualBinaryContingencyTable()

Method Summary

int	an() Actual Negatives
int	ap() Actual Positives
double	approximateCorrelation() This is the approximate correlation.
double	averageConditionalProbability() This is the average conditional probability.
double	averageSensitivitySpecificity() This is the average of sensitivity and specifity.
double	correlationCoefficient() This is the Pearson correlation of two 0-1 random variables X=prediction and Y=reality CC = Cov(X,Y)/(Stddev(X)*Stddev(Y)) If either RV has zero variance, the CC is underfined: assertion faliure If this contingency table is not tracking TN, then CC is undefined: assertion failure
void	forgetTN()
void	freeze()
int	getFN()
int	getFP()
int	getTN()
int	getTP()
void	increment(boolean predicted, boolean actual)
void	incrementFN()
void	incrementFP()
void	incrementTN()
void	incrementTP()
int	pn() Predicted Negatives
int	pp() Predicted Positives
double	sensitivity() Sensitivity is TP/(TP+FN) is the fraction of actual events that are predicted.
void	set(int tp, int fp, int fn)
void	set(int tp, int fp, int fn, int tn)
double	specificity() Specificity is the TP/(TP+FP) is the fraction of predicted events that are real.
java.lang.String	summarize()

Methods inherited from class java.lang.Object

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

Constructor Detail

PredictedActualBinaryContingencyTable

public PredictedActualBinaryContingencyTable()

Method Detail

set

public void set(int tp,
                int fp,
                int fn,
                int tn)

set

public void set(int tp,
                int fp,
                int fn)

forgetTN

public void forgetTN()

incrementTP

public void incrementTP()

incrementFP

public void incrementFP()

incrementFN

public void incrementFN()

incrementTN

public void incrementTN()

increment

public void increment(boolean predicted,
                      boolean actual)

freeze

public void freeze()

getTP

public int getTP()

getFP

public int getFP()

getFN

public int getFN()

getTN

public int getTN()

ap

public int ap()

Actual Positives

an

public int an()

Actual Negatives

pp

public int pp()

Predicted Positives

pn

public int pn()

Predicted Negatives

correlationCoefficient

public double correlationCoefficient()

This is the Pearson correlation of two 0-1 random variables X=prediction and Y=reality CC = Cov(X,Y)/(Stddev(X)*Stddev(Y)) If either RV has zero variance, the CC is underfined: assertion faliure If this contingency table is not tracking TN, then CC is undefined: assertion failure

averageConditionalProbability

public double averageConditionalProbability()

This is the average conditional probability. Only defined if TN is being tracked, and if all four marginal values are positive.

approximateCorrelation

public double approximateCorrelation()

This is the approximate correlation. Only defined if TN is being tracked, and if all four marginal values are positive. Equal to 2*(averageConditionalProbability - 0.5)

averageSensitivitySpecificity

public double averageSensitivitySpecificity()

This is the average of sensitivity and specifity. This is equal to the limit of ACP as TN->infinity This is defined even if we are not tracking TN.

sensitivity

public double sensitivity()

Sensitivity is TP/(TP+FN) is the fraction of actual events that are predicted. If TP+FN is zero then sensitivity is undefined, resulting in assertion failure Sensitivity is defined even if not tracking TN.

specificity

public double specificity()

Specificity is the TP/(TP+FP) is the fraction of predicted events that are real. If TP+FP=0 then specificity is undefined and result in assertion failure Specificity is defined even if not tracking TN

summarize

public java.lang.String summarize()