org.dkpro.statistics.agreement

Class DisagreementMeasure

java.lang.Object

org.dkpro.statistics.agreement.DisagreementMeasure

All Implemented Interfaces:

IAgreementMeasure

Direct Known Subclasses:

UnitizingAgreementMeasure, WeightedAgreement

public abstract class DisagreementMeasure
extends Object
implements IAgreementMeasure

Default implementation of the IAgreementMeasure interface providing computational hooks for calculating the observed and the expected disagreement. The values for observed and expected disagreement are combined using Krippendorff's (1980)1 - (D_O / D_E) formula (where D_O denotes the observed disagreement and D_E denotes the expected disagreement. See also AgreementMeasure for the analogous definition of a measure based on the observed and expected agreement.

References:

• Krippendorff, K.: Content Analysis: An Introduction to Its Methodology. Beverly Hills, CA: Sage Publications, 1980.

Author:

Christian M. Meyer

See Also:

IAgreementMeasure, AgreementMeasure

Constructor Summary

Constructors

Constructor and Description
DisagreementMeasure()

Method Summary

Modifier and Type	Method and Description
double	calculateAgreement() Returns the inter-rater agreement score.
protected double	calculateExpectedDisagreement()
protected abstract double	calculateObservedDisagreement()

Methods inherited from class java.lang.Object

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

Constructor Detail

DisagreementMeasure

public DisagreementMeasure()

Method Detail

calculateAgreement

public double calculateAgreement()

Description copied from interface: IAgreementMeasure

Returns the inter-rater agreement score. Unless otherwise indicated, the result is between -1 and +1, where +1 indicates perfect agreement, 0 indicates no agreement or that the agreement can be fully explained by chance, and -1 indicates perfect disagreement.

Specified by:

calculateAgreement in interface IAgreementMeasure

calculateObservedDisagreement

protected abstract double calculateObservedDisagreement()

calculateExpectedDisagreement

protected double calculateExpectedDisagreement()