Bias-corrected estimation of the Rudas-Clogg-Lindsay mixture index of fit

J. Reiczigel, Márton Ispány, Gábor Tusnády, György Michaletzky, Marco Marozzi

Research output: Contribution to journalArticle

Abstract

Rudas, Clogg, and Lindsay (1994, J. R Stat Soc. Ser. B, 56, 623) introduced the so-called mixture index of fit, also known as pi-star (Π*), for quantifying the goodness of fit of a model. It is the lowest proportion of 'contamination' which, if removed from the population or from the sample, makes the fit of the model perfect. The mixture index of fit has been widely used in psychometric studies. We show that the asymptotic confidence limits proposed by Rudas et al. (1994, J. R Stat Soc. Ser. B, 56, 623) as well as the jackknife confidence interval by Dayton (2003, Br. J. Math. Stat. Psychol., 56, 1) perform poorly, and propose a new bias-corrected point estimate, a bootstrap test and confidence limits for pi-star. The proposed confidence limits have coverage probability much closer to the nominal level than the other methods do. We illustrate the usefulness of the proposed method in practice by presenting some practical applications to log-linear models for contingency tables.

Original languageEnglish
JournalBritish Journal of Mathematical and Statistical Psychology
DOIs
Publication statusAccepted/In press - Jan 1 2018

Fingerprint

Confidence Limits
Pi
Star
Psychometrics
Bootstrap Test
Linear Models
Log-linear Models
Jackknife
Point Estimate
Asymptotic Limit
Contingency Table
Coverage Probability
Confidence Intervals
Goodness of fit
Contamination
Categorical or nominal
Confidence interval
Lowest
Proportion
Population

ASJC Scopus subject areas

  • Statistics and Probability
  • Arts and Humanities (miscellaneous)
  • Psychology(all)

Cite this

Bias-corrected estimation of the Rudas-Clogg-Lindsay mixture index of fit. / Reiczigel, J.; Ispány, Márton; Tusnády, Gábor; Michaletzky, György; Marozzi, Marco.

In: British Journal of Mathematical and Statistical Psychology, 01.01.2018.

Research output: Contribution to journalArticle

@article{e7668982964d45cc99f04c97f44d8250,
title = "Bias-corrected estimation of the Rudas-Clogg-Lindsay mixture index of fit",
abstract = "Rudas, Clogg, and Lindsay (1994, J. R Stat Soc. Ser. B, 56, 623) introduced the so-called mixture index of fit, also known as pi-star (Π*), for quantifying the goodness of fit of a model. It is the lowest proportion of 'contamination' which, if removed from the population or from the sample, makes the fit of the model perfect. The mixture index of fit has been widely used in psychometric studies. We show that the asymptotic confidence limits proposed by Rudas et al. (1994, J. R Stat Soc. Ser. B, 56, 623) as well as the jackknife confidence interval by Dayton (2003, Br. J. Math. Stat. Psychol., 56, 1) perform poorly, and propose a new bias-corrected point estimate, a bootstrap test and confidence limits for pi-star. The proposed confidence limits have coverage probability much closer to the nominal level than the other methods do. We illustrate the usefulness of the proposed method in practice by presenting some practical applications to log-linear models for contingency tables.",
author = "J. Reiczigel and M{\'a}rton Isp{\'a}ny and G{\'a}bor Tusn{\'a}dy and Gy{\"o}rgy Michaletzky and Marco Marozzi",
year = "2018",
month = "1",
day = "1",
doi = "10.1111/bmsp.12118",
language = "English",
journal = "British Journal of Mathematical and Statistical Psychology",
issn = "0007-1102",
publisher = "Wiley-Blackwell",

}

TY - JOUR

T1 - Bias-corrected estimation of the Rudas-Clogg-Lindsay mixture index of fit

AU - Reiczigel, J.

AU - Ispány, Márton

AU - Tusnády, Gábor

AU - Michaletzky, György

AU - Marozzi, Marco

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Rudas, Clogg, and Lindsay (1994, J. R Stat Soc. Ser. B, 56, 623) introduced the so-called mixture index of fit, also known as pi-star (Π*), for quantifying the goodness of fit of a model. It is the lowest proportion of 'contamination' which, if removed from the population or from the sample, makes the fit of the model perfect. The mixture index of fit has been widely used in psychometric studies. We show that the asymptotic confidence limits proposed by Rudas et al. (1994, J. R Stat Soc. Ser. B, 56, 623) as well as the jackknife confidence interval by Dayton (2003, Br. J. Math. Stat. Psychol., 56, 1) perform poorly, and propose a new bias-corrected point estimate, a bootstrap test and confidence limits for pi-star. The proposed confidence limits have coverage probability much closer to the nominal level than the other methods do. We illustrate the usefulness of the proposed method in practice by presenting some practical applications to log-linear models for contingency tables.

AB - Rudas, Clogg, and Lindsay (1994, J. R Stat Soc. Ser. B, 56, 623) introduced the so-called mixture index of fit, also known as pi-star (Π*), for quantifying the goodness of fit of a model. It is the lowest proportion of 'contamination' which, if removed from the population or from the sample, makes the fit of the model perfect. The mixture index of fit has been widely used in psychometric studies. We show that the asymptotic confidence limits proposed by Rudas et al. (1994, J. R Stat Soc. Ser. B, 56, 623) as well as the jackknife confidence interval by Dayton (2003, Br. J. Math. Stat. Psychol., 56, 1) perform poorly, and propose a new bias-corrected point estimate, a bootstrap test and confidence limits for pi-star. The proposed confidence limits have coverage probability much closer to the nominal level than the other methods do. We illustrate the usefulness of the proposed method in practice by presenting some practical applications to log-linear models for contingency tables.

UR - http://www.scopus.com/inward/record.url?scp=85042531532&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042531532&partnerID=8YFLogxK

U2 - 10.1111/bmsp.12118

DO - 10.1111/bmsp.12118

M3 - Article

JO - British Journal of Mathematical and Statistical Psychology

JF - British Journal of Mathematical and Statistical Psychology

SN - 0007-1102

ER -