The Performance of Local Dependence Measures With Psychological Data

Carrie R. Houts, Michael Edwards

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The violation of the assumption of local independence when applying item response theory (IRT) models has been shown to have a negative impact on all estimates obtained from the given model. Numerous indices and statistics have been proposed to aid analysts in the detection of local dependence (LD). A Monte Carlo study was conducted to evaluate the relative performance of selected LD measures in conditions considered typical of studies collecting psychological assessment data. Both the Jackknife Slope Index and likelihood ratio statistic G2 are available across the two IRT models used and displayed adequate to good performance in most simulation conditions. The use of these indices together is the final recommendation for applied analysts. Future research areas are discussed.

Original languageEnglish (US)
Pages (from-to)541-562
Number of pages22
JournalApplied Psychological Measurement
Volume37
Issue number7
DOIs
StatePublished - Oct 1 2013
Externally publishedYes

Fingerprint

model theory
Psychology
statistics
performance
simulation

Keywords

  • 2PLM
  • GRM
  • IRT
  • LD measures
  • local dependence

ASJC Scopus subject areas

  • Social Sciences (miscellaneous)
  • Psychology (miscellaneous)

Cite this

The Performance of Local Dependence Measures With Psychological Data. / Houts, Carrie R.; Edwards, Michael.

In: Applied Psychological Measurement, Vol. 37, No. 7, 01.10.2013, p. 541-562.

Research output: Contribution to journalArticle

@article{a60cb546a8624fbcb791a2c4339dc80d,
title = "The Performance of Local Dependence Measures With Psychological Data",
abstract = "The violation of the assumption of local independence when applying item response theory (IRT) models has been shown to have a negative impact on all estimates obtained from the given model. Numerous indices and statistics have been proposed to aid analysts in the detection of local dependence (LD). A Monte Carlo study was conducted to evaluate the relative performance of selected LD measures in conditions considered typical of studies collecting psychological assessment data. Both the Jackknife Slope Index and likelihood ratio statistic G2 are available across the two IRT models used and displayed adequate to good performance in most simulation conditions. The use of these indices together is the final recommendation for applied analysts. Future research areas are discussed.",
keywords = "2PLM, GRM, IRT, LD measures, local dependence",
author = "Houts, {Carrie R.} and Michael Edwards",
year = "2013",
month = "10",
day = "1",
doi = "10.1177/0146621613491456",
language = "English (US)",
volume = "37",
pages = "541--562",
journal = "Applied Psychological Measurement",
issn = "0146-6216",
publisher = "SAGE Publications Inc.",
number = "7",

}

TY - JOUR

T1 - The Performance of Local Dependence Measures With Psychological Data

AU - Houts, Carrie R.

AU - Edwards, Michael

PY - 2013/10/1

Y1 - 2013/10/1

N2 - The violation of the assumption of local independence when applying item response theory (IRT) models has been shown to have a negative impact on all estimates obtained from the given model. Numerous indices and statistics have been proposed to aid analysts in the detection of local dependence (LD). A Monte Carlo study was conducted to evaluate the relative performance of selected LD measures in conditions considered typical of studies collecting psychological assessment data. Both the Jackknife Slope Index and likelihood ratio statistic G2 are available across the two IRT models used and displayed adequate to good performance in most simulation conditions. The use of these indices together is the final recommendation for applied analysts. Future research areas are discussed.

AB - The violation of the assumption of local independence when applying item response theory (IRT) models has been shown to have a negative impact on all estimates obtained from the given model. Numerous indices and statistics have been proposed to aid analysts in the detection of local dependence (LD). A Monte Carlo study was conducted to evaluate the relative performance of selected LD measures in conditions considered typical of studies collecting psychological assessment data. Both the Jackknife Slope Index and likelihood ratio statistic G2 are available across the two IRT models used and displayed adequate to good performance in most simulation conditions. The use of these indices together is the final recommendation for applied analysts. Future research areas are discussed.

KW - 2PLM

KW - GRM

KW - IRT

KW - LD measures

KW - local dependence

UR - http://www.scopus.com/inward/record.url?scp=84884144947&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84884144947&partnerID=8YFLogxK

U2 - 10.1177/0146621613491456

DO - 10.1177/0146621613491456

M3 - Article

VL - 37

SP - 541

EP - 562

JO - Applied Psychological Measurement

JF - Applied Psychological Measurement

SN - 0146-6216

IS - 7

ER -