com.itemanalysis.psychometrics.irt.estimation

Class ItemFitSX2

java.lang.Object

com.itemanalysis.psychometrics.irt.estimation.AbstractItemFitStatistic

com.itemanalysis.psychometrics.irt.estimation.ItemFitSX2

All Implemented Interfaces:

ItemFitStatistic

public class ItemFitSX2
extends AbstractItemFitStatistic

Computes the generalized S-X2 statistic developed by: Kang, T., and Chen, T., T. (2007). An investigation of the performance of the generalized S-X2 item-fit index for polytomous IRT models. ACT Research Report Series 2007-1. ACT: Iowa City, Iowa. For a test of all binary items, this statistic is identical to Orlando and Thissen's S-X2 statistic that is descrined in: Orlando, M., and Thissen, D. (2000). Likelihood based item-fit indices for dichotomous item response theory models. Applied Psychological Measurement, 24(1), 50-64. This implementation differs from that described in Kang and Chen (2007) in one major way. The table is collapsed across rows only. No collapsing is done over response categories. Any row with an average expected value less than 1 will be collapsed (see Orlando and Thissen, 2000).

Field Summary

Fields inherited from class com.itemanalysis.psychometrics.irt.estimation.AbstractItemFitStatistic

expectedValues, irm, minExpectedCellCount, numberOfBins, numberOfCategories, rowMargin, rowThetaSum, table, totalCount, validRow

Constructor Summary

Constructors

Constructor and Description
ItemFitSX2(IrtObservedScoreDistribution irtObservedScoreDistribution, IrtObservedScoreDistribution irtObservedScoreDistributionWithoutItem, ItemResponseModel irm, int maxTestScorePlusOne, int minExpectedCellCount)

Method Summary

Modifier and Type	Method and Description
void	compute()
protected void	condenseTable()
double	getDegreesOfFreedom()
double	getPValue()
double	getThetaAt(int i)
double	getValue()
void	increment(int summedScore, int itemResponse) Increment fit statistic assuming there is a table row for each possible summed score.
void	increment(int summedScore, int itemResponse, double frequency)
java.lang.String	toString()

Methods inherited from class com.itemanalysis.psychometrics.irt.estimation.AbstractItemFitStatistic

getFrequencyAt, getProportionAt, getTotalCount, initialize, printContingencyTable, printMirtFormatTable

Methods inherited from class java.lang.Object

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

Constructor Detail

ItemFitSX2

public ItemFitSX2(IrtObservedScoreDistribution irtObservedScoreDistribution,
                  IrtObservedScoreDistribution irtObservedScoreDistributionWithoutItem,
                  ItemResponseModel irm,
                  int maxTestScorePlusOne,
                  int minExpectedCellCount)

Method Detail

increment

public void increment(int summedScore,
                      int itemResponse)

Increment fit statistic assuming there is a table row for each possible summed score. ItemFitChiSquare(ItemResponseModel irm, int numberOfBins, int minExpectedCellCount)

Parameters:

summedScore - summed score value.

itemResponse - an item response.

increment

public void increment(int summedScore,
                      int itemResponse,
                      double frequency)

condenseTable

protected void condenseTable()

Overrides:

condenseTable in class AbstractItemFitStatistic

getThetaAt

public double getThetaAt(int i)

compute

public void compute()

getValue

public double getValue()

getDegreesOfFreedom

public double getDegreesOfFreedom()

getPValue

public double getPValue()

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object