IMPACT_S

Class Statistics

java.lang.Object

IMPACT_S.Statistics

public class Statistics
extends java.lang.Object

Class implementing some distributions, tests, etc. Most of the code is adapted from Gary Perlman's unixstat.

This class is originally from "package weka.core" authored by Eibe Frank.
It was adpated to serve as Statistics API to IMPACT_S. The function chiSquaredCritical() was added to provide support for LRT tests.
This new function is also based on the original Gary Perlman's code.

Version:

Original $ Revision: 1.4 $

Author:

Emanuel Maldonado (EM), Eibe Frank (eibe@cs.waikato.ac.nz)

Constructor Summary

Constructors

Constructor and Description
Statistics()

Method Summary

Modifier and Type	Method and Description
double	binomialStandardError(double p, int n) Computes standard error for observed values of a binomial random variable.
double	chiSquaredCritical(double p, int df) Returns critical chi-square value for given significance and degrees of freedom.
double	chiSquaredProbability(double x, int df) Returns chi-squared probability for given value and degrees of freedom.
double	FCriticalValue(double p, int df1, int df2) Critical value for given probability of F-distribution.
double	FProbability(double F, int df1, int df2) Computes probability of F-ratio.
double	normalProbability(double z) Returns probability that the standardized normal variate Z (mean = 0, standard deviation = 1) is less than z.
double	studentTConfidenceInterval(int df, double p, double se) Computes absolute size of half of a student-t confidence interval for given degrees of freedom, probability, and observed value.

Methods inherited from class java.lang.Object

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

Constructor Detail

Statistics

public Statistics()

Method Detail

binomialStandardError

public double binomialStandardError(double p,
                                    int n)

Computes standard error for observed values of a binomial random variable.

Parameters:

p - the probability of success

n - the size of the sample

Returns:

the standard error

chiSquaredProbability

public double chiSquaredProbability(double x,
                                    int df)

Returns chi-squared probability for given value and degrees of freedom. (The probability that the chi-squared variate will be greater than x for the given degrees of freedom.) Adapted from unixstat by Gary Perlman.

Parameters:

x - the value

df - the number of degrees of freedom

Returns:

chi-square probability.

chiSquaredCritical

public double chiSquaredCritical(double p,
                                 int df)

Returns critical chi-square value for given significance and degrees of freedom. (The critical value to produce the given significance) Adapted from chisq.c by Gary Perlman. http://hcibib.org/perlman/stat/doc/chisq.c Author: Emanuel Maldonado

Parameters:

p - the significance

df - the number of degrees of freedom

Returns:

the critical chi-square value.

FCriticalValue

public double FCriticalValue(double p,
                             int df1,
                             int df2)

Critical value for given probability of F-distribution. Adapted from unixstat by Gary Perlman.

Parameters:

p - the probability

df1 - the first number of degrees of freedom

df2 - the second number of degrees of freedom

Returns:

the critical value for the given probability

FProbability

public double FProbability(double F,
                           int df1,
                           int df2)

Computes probability of F-ratio. Adapted from unixstat by Gary Perlman. Collected Algorithms of the CACM Algorithm 322 Egon Dorrer

Parameters:

F - the F-ratio

df1 - the first number of degrees of freedom

df2 - the second number of degrees of freedom

Returns:

the probability of the F-ratio.

normalProbability

public double normalProbability(double z)

Returns probability that the standardized normal variate Z (mean = 0, standard deviation = 1) is less than z. Adapted from unixstat by Gary Perlman.

Parameters:

z - the z-value

Returns:

the probability of the z value according to the normal pdf

studentTConfidenceInterval

public double studentTConfidenceInterval(int df,
                                         double p,
                                         double se)

Computes absolute size of half of a student-t confidence interval for given degrees of freedom, probability, and observed value.

Parameters:

df - the number of degrees of freedom

p - the probability

se - the observed value

Returns:

absolute size of half of a student-t confidence interval