gov.sandia.cognition.statistics.method
Class AnalysisOfVarianceOneWay

java.lang.Object
  extended by gov.sandia.cognition.util.AbstractCloneableSerializable
      extended by gov.sandia.cognition.statistics.method.AnalysisOfVarianceOneWay
All Implemented Interfaces:
BlockExperimentComparison<Number>, NullHypothesisEvaluator<Collection<? extends Number>>, CloneableSerializable, Serializable, Cloneable

@ConfidenceTestAssumptions(name="One-Way Analysis of Variance",
                           alsoKnownAs={"1-way ANOVA","Fixed-effects 1-way ANOVA","F test"},
                           description={"ANOVA tests to determine if the means between the various treatments are equal.","ANOVA is a generalization of the paired Student t-test, where there can be multiple treatments.","When there are two groups, a control group and a treatment group, ANOVA is equivalent to the unpaired t-test."},
                           assumptions={"The data are sampled from a Gaussian distribution.","The variance within the different groups is equal.","The data from each group is collected independently of each other."},
                           nullHypothesis="The means from all groups are equal.",
                           dataPaired=false,
                           dataSameSize=false,
                           distribution=SnedecorFDistribution.CDF.class,
                           reference=@PublicationReference(author="Wikipedia",title="Analysis of Variance",type=WebPage,year=2009,url="http://en.wikipedia.org/wiki/Analysis_of_variance"))
public class AnalysisOfVarianceOneWay
extends AbstractCloneableSerializable
implements BlockExperimentComparison<Number>

Analysis of Variance single-factor null-hypothesis testing procedure, usually called "1-way ANOVA". ANOVA evaluates the probability of the null hypothesis for a Collection of treatment cases. Each "treatment" is an experiment with a Collection of results from a given population. You can have different population sizes in each treatment. The null hypothesis is that there are no differences between the populations and that observed differences are due to chance.

Since:
2.0
Author:
Kevin R. Dixon
See Also:
Serialized Form

Nested Class Summary
static class AnalysisOfVarianceOneWay.Statistic
          Returns the confidence statistic for an ANOVA test
 
Field Summary
static AnalysisOfVarianceOneWay INSTANCE
          Default instance.
 
Constructor Summary
AnalysisOfVarianceOneWay()
          Creates a new instance of AnalysisOfVarianceOneWay
 
Method Summary
 AnalysisOfVarianceOneWay.Statistic evaluateNullHypothesis(Collection<? extends Collection<? extends Number>> data)
          Evaluates the null hypothesis for the given block-design treatments
 AnalysisOfVarianceOneWay.Statistic evaluateNullHypothesis(Collection<? extends Number> data1, Collection<? extends Number> data2)
          Evaluates the ANOVA statistics for the two given treatments, each treatment can have a different number of samples
 
Methods inherited from class gov.sandia.cognition.util.AbstractCloneableSerializable
clone
 
Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 
Methods inherited from interface gov.sandia.cognition.util.CloneableSerializable
clone
 

Field Detail

INSTANCE

public static final AnalysisOfVarianceOneWay INSTANCE
Default instance.

Constructor Detail

AnalysisOfVarianceOneWay

public AnalysisOfVarianceOneWay()
Creates a new instance of AnalysisOfVarianceOneWay

Method Detail

evaluateNullHypothesis

@PublicationReference(author={"Frederick J. Gravetter","Larry B. Wallnau"},
                      title="Statistics for the Behavioral Sciences",
                      type=Book,
                      year=2003,
                      pages={406,412},
                      notes="Chapter 13.3")
public AnalysisOfVarianceOneWay.Statistic evaluateNullHypothesis(Collection<? extends Collection<? extends Number>> data)
Description copied from interface: BlockExperimentComparison
Evaluates the null hypothesis for the given block-design treatments

Specified by:
evaluateNullHypothesis in interface BlockExperimentComparison<Number>
Parameters:
data - Collection of treatments for the block-design experiment, where each treatment contains
Returns:
The confidence for the null hypothesis.

evaluateNullHypothesis

public AnalysisOfVarianceOneWay.Statistic evaluateNullHypothesis(Collection<? extends Number> data1,
                                                                 Collection<? extends Number> data2)
Evaluates the ANOVA statistics for the two given treatments, each treatment can have a different number of samples

Specified by:
evaluateNullHypothesis in interface NullHypothesisEvaluator<Collection<? extends Number>>
Parameters:
data1 - First treatment
data2 - Second treatment
Returns:
ANOVA Confidence statistics