14 Citations (Scopus)

Abstract

The goodness-of-fit test based on Pearson's chi-squared statistic is sometimes considered to be an omnibus test that gives little guidance to the source of poor fit when the null hypothesis is rejected. It has also been recognized that the omnibus test can often be outperformed by focused or directional tests of lower order. In this paper, a test is considered for a model on a data table formed by the cross-classification of q dichotomous variables, and a score statistic on overlapping cells that correspond to the first- through qth-order marginal frequencies is presented. Then orthogonal components of the Pearson-Fisher statistic are defined on marginal frequencies. The orthogonal components may be used to form test statistics, and a log-linear version of an item response model is used to investigate the order and dilution of a test based on these components, as well as the projection of components onto the space of lower-order marginals. The advantage of the components in terms of power and detection of the source of poor fit is demonstrated. Overcoming the adverse effects of sparseness provides another motive for using components based on marginal frequencies because an asymptotic chi-squared distribution will be more reliable for a statistic formed on overlapping cells if expected frequencies in the joint distribution are small.

Original languageEnglish (US)
Pages (from-to)331-360
Number of pages30
JournalBritish Journal of Mathematical and Statistical Psychology
Volume61
Issue number2
DOIs
StatePublished - Nov 2008

Fingerprint

Goodness of fit
Testing
Omnibus Test
Statistic
Overlapping
Electric Power Supplies
Chi-squared distribution
Score Statistic
Chi-squared
Cell
Goodness of Fit Test
Joint Distribution
Null hypothesis
Asymptotic distribution
Test Statistic
Guidance
Goodness
Table
Projection
Statistics

ASJC Scopus subject areas

  • Psychology(all)
  • Statistics and Probability

Cite this

@article{d8d2e8bab9e84589a76ec1af596024b8,
title = "Goodness-of-fit testing using components based on marginal frequencies of multinomial data",
abstract = "The goodness-of-fit test based on Pearson's chi-squared statistic is sometimes considered to be an omnibus test that gives little guidance to the source of poor fit when the null hypothesis is rejected. It has also been recognized that the omnibus test can often be outperformed by focused or directional tests of lower order. In this paper, a test is considered for a model on a data table formed by the cross-classification of q dichotomous variables, and a score statistic on overlapping cells that correspond to the first- through qth-order marginal frequencies is presented. Then orthogonal components of the Pearson-Fisher statistic are defined on marginal frequencies. The orthogonal components may be used to form test statistics, and a log-linear version of an item response model is used to investigate the order and dilution of a test based on these components, as well as the projection of components onto the space of lower-order marginals. The advantage of the components in terms of power and detection of the source of poor fit is demonstrated. Overcoming the adverse effects of sparseness provides another motive for using components based on marginal frequencies because an asymptotic chi-squared distribution will be more reliable for a statistic formed on overlapping cells if expected frequencies in the joint distribution are small.",
author = "Mark Reiser",
year = "2008",
month = "11",
doi = "10.1348/000711007X204215",
language = "English (US)",
volume = "61",
pages = "331--360",
journal = "British Journal of Mathematical and Statistical Psychology",
issn = "0007-1102",
publisher = "Wiley-Blackwell",
number = "2",

}

TY - JOUR

T1 - Goodness-of-fit testing using components based on marginal frequencies of multinomial data

AU - Reiser, Mark

PY - 2008/11

Y1 - 2008/11

N2 - The goodness-of-fit test based on Pearson's chi-squared statistic is sometimes considered to be an omnibus test that gives little guidance to the source of poor fit when the null hypothesis is rejected. It has also been recognized that the omnibus test can often be outperformed by focused or directional tests of lower order. In this paper, a test is considered for a model on a data table formed by the cross-classification of q dichotomous variables, and a score statistic on overlapping cells that correspond to the first- through qth-order marginal frequencies is presented. Then orthogonal components of the Pearson-Fisher statistic are defined on marginal frequencies. The orthogonal components may be used to form test statistics, and a log-linear version of an item response model is used to investigate the order and dilution of a test based on these components, as well as the projection of components onto the space of lower-order marginals. The advantage of the components in terms of power and detection of the source of poor fit is demonstrated. Overcoming the adverse effects of sparseness provides another motive for using components based on marginal frequencies because an asymptotic chi-squared distribution will be more reliable for a statistic formed on overlapping cells if expected frequencies in the joint distribution are small.

AB - The goodness-of-fit test based on Pearson's chi-squared statistic is sometimes considered to be an omnibus test that gives little guidance to the source of poor fit when the null hypothesis is rejected. It has also been recognized that the omnibus test can often be outperformed by focused or directional tests of lower order. In this paper, a test is considered for a model on a data table formed by the cross-classification of q dichotomous variables, and a score statistic on overlapping cells that correspond to the first- through qth-order marginal frequencies is presented. Then orthogonal components of the Pearson-Fisher statistic are defined on marginal frequencies. The orthogonal components may be used to form test statistics, and a log-linear version of an item response model is used to investigate the order and dilution of a test based on these components, as well as the projection of components onto the space of lower-order marginals. The advantage of the components in terms of power and detection of the source of poor fit is demonstrated. Overcoming the adverse effects of sparseness provides another motive for using components based on marginal frequencies because an asymptotic chi-squared distribution will be more reliable for a statistic formed on overlapping cells if expected frequencies in the joint distribution are small.

UR - http://www.scopus.com/inward/record.url?scp=56649088100&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56649088100&partnerID=8YFLogxK

U2 - 10.1348/000711007X204215

DO - 10.1348/000711007X204215

M3 - Article

C2 - 17535483

AN - SCOPUS:56649088100

VL - 61

SP - 331

EP - 360

JO - British Journal of Mathematical and Statistical Psychology

JF - British Journal of Mathematical and Statistical Psychology

SN - 0007-1102

IS - 2

ER -