Posterior predictive checks for conditional independence between response time and accuracy

Maria Bolsinova, J. Tijmstra

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Conditional independence (CI) between response time and response accuracy is a fundamental assumption of many joint models for time and accuracy used in educational measurement. In this study, posterior predictive checks (PPCs) are proposed for testing this assumption. These PPCs are based on three discrepancy measures reflecting different observable consequences of different types of violations of CI. Simulation studies are performed to evaluate the specificity of the procedure, its robustness, and its sensitivity to detect different types of conditional dependence and to compare it to existing methods. The new procedure outperforms the existing methods in most of the simulation conditions. The use of the PPCs is illustrated using arithmetics test data.
Original languageEnglish
Pages (from-to)123-145
JournalJournal of Educational and Behavioral Statistics
Volume41
Issue number2
DOIs
Publication statusPublished - 2016

Keywords

  • conditional independence
  • item response theory
  • hierarchical model
  • posterior predictive checks
  • response times

Cite this

@article{39c014187d8343f1b2d73163ca261f2f,
title = "Posterior predictive checks for conditional independence between response time and accuracy",
abstract = "Conditional independence (CI) between response time and response accuracy is a fundamental assumption of many joint models for time and accuracy used in educational measurement. In this study, posterior predictive checks (PPCs) are proposed for testing this assumption. These PPCs are based on three discrepancy measures reflecting different observable consequences of different types of violations of CI. Simulation studies are performed to evaluate the specificity of the procedure, its robustness, and its sensitivity to detect different types of conditional dependence and to compare it to existing methods. The new procedure outperforms the existing methods in most of the simulation conditions. The use of the PPCs is illustrated using arithmetics test data.",
keywords = "conditional independence, item response theory, hierarchical model, posterior predictive checks, response times",
author = "Maria Bolsinova and J. Tijmstra",
year = "2016",
doi = "10.3102/1076998616631746",
language = "English",
volume = "41",
pages = "123--145",
journal = "Journal of Educational and Behavioral Statistics",
issn = "1076-9986",
publisher = "Sage Publications, Inc.",
number = "2",

}

Posterior predictive checks for conditional independence between response time and accuracy. / Bolsinova, Maria; Tijmstra, J.

In: Journal of Educational and Behavioral Statistics, Vol. 41, No. 2, 2016, p. 123-145.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Posterior predictive checks for conditional independence between response time and accuracy

AU - Bolsinova, Maria

AU - Tijmstra, J.

PY - 2016

Y1 - 2016

N2 - Conditional independence (CI) between response time and response accuracy is a fundamental assumption of many joint models for time and accuracy used in educational measurement. In this study, posterior predictive checks (PPCs) are proposed for testing this assumption. These PPCs are based on three discrepancy measures reflecting different observable consequences of different types of violations of CI. Simulation studies are performed to evaluate the specificity of the procedure, its robustness, and its sensitivity to detect different types of conditional dependence and to compare it to existing methods. The new procedure outperforms the existing methods in most of the simulation conditions. The use of the PPCs is illustrated using arithmetics test data.

AB - Conditional independence (CI) between response time and response accuracy is a fundamental assumption of many joint models for time and accuracy used in educational measurement. In this study, posterior predictive checks (PPCs) are proposed for testing this assumption. These PPCs are based on three discrepancy measures reflecting different observable consequences of different types of violations of CI. Simulation studies are performed to evaluate the specificity of the procedure, its robustness, and its sensitivity to detect different types of conditional dependence and to compare it to existing methods. The new procedure outperforms the existing methods in most of the simulation conditions. The use of the PPCs is illustrated using arithmetics test data.

KW - conditional independence

KW - item response theory

KW - hierarchical model

KW - posterior predictive checks

KW - response times

U2 - 10.3102/1076998616631746

DO - 10.3102/1076998616631746

M3 - Article

VL - 41

SP - 123

EP - 145

JO - Journal of Educational and Behavioral Statistics

JF - Journal of Educational and Behavioral Statistics

SN - 1076-9986

IS - 2

ER -