All Packages  Class Hierarchy  This Package  Previous  Next  Index  WEKA's home

Class weka.experiment.PairedStats 

java.lang.Object
   |
   +----weka.experiment.PairedStats
public class PairedStats
extends Object
A class for storing stats on a paired comparison (t-test and correlation)

Version:
$Revision: 1.2 $
Author:
Len Trigg (trigg@cs.waikato.ac.nz)

Variable Index

o correlation
The correlation coefficient
o count
The number of data points seen
o differencesProbability
The probability of obtaining the observed differences
o differencesSignificance
A significance indicator: 0 if the differences are not significant > 0 if x significantly greater than y < 0 if x significantly less than y
o differencesStats
The stats associated with the paired differences
o sigLevel
The significance level for comparisons
o xStats
The stats associated with the data in column 1
o xySum
The sum of the products
o yStats
The stats associated with the data in column 2

Constructor Index

o PairedStats(double)
Creates a new PairedStats object with the supplied significance level.

Method Index

o add(double, double)
Add an observed pair of values.
o calculateDerived()
Calculates the derived statistics (significance etc).
o main(String[])
Tests the paired stats object from the command line.
o subtract(double, double)
Removes an observed pair of values.
o toString()
Returns statistics on the paired comparison.

Variables

o xStats 
 public Stats xStats
The stats associated with the data in column 1

o yStats 
 public Stats yStats
The stats associated with the data in column 2

o differencesStats 
 public Stats differencesStats
The stats associated with the paired differences

o differencesProbability 
 public double differencesProbability
The probability of obtaining the observed differences

o correlation 
 public double correlation
The correlation coefficient

o xySum 
 public double xySum
The sum of the products

o count 
 public double count
The number of data points seen

o differencesSignificance 
 public int differencesSignificance
A significance indicator: 0 if the differences are not significant > 0 if x significantly greater than y < 0 if x significantly less than y

o sigLevel 
 public double sigLevel
The significance level for comparisons

Constructors

o PairedStats 
 public PairedStats(double sig)
Creates a new PairedStats object with the supplied significance level.

Parameters:
sig - the significance level for comparisons

Methods

o add 
 public void add(double value1,
                 double value2)
Add an observed pair of values.

Parameters:
value1 - the value from column 1
value2 - the value from column 2
o subtract 
 public void subtract(double value1,
                      double value2)
Removes an observed pair of values.

Parameters:
value1 - the value from column 1
value2 - the value from column 2
o calculateDerived 
 public void calculateDerived()
Calculates the derived statistics (significance etc).

o toString 
 public String toString()
Returns statistics on the paired comparison.

Returns:
the t-test statistics as a string
Overrides:
toString in class Object
o main 
 public static void main(String args[])
Tests the paired stats object from the command line. reads line from stdin, expecting two values per line.

Parameters:
args - ignored. 
All Packages  Class Hierarchy  This Package  Previous  Next  Index  WEKA's home