Statistic lz based person-fit methods for non-cognitive multiscale measures

J.M. Conijn, W.H.M. Emons, K. Sijtsma

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Most person-fit statistics require long tests to reliably detect aberrant item-score vectors and are not readily applicable to noncognitive measures that consist of multiple short subscales. The authors propose combining subscale person-fit information to detect aberrant item-score vectors on noncognitive multiscale measures. They used a simulation study and three empirical personality and psychopathology test datasets to assess five multiscale person-fit methods based on the lz person-fit statistic with respect to (a) identifying aberrant item-score vectors, (b) improving accuracy of research results, and (c) understanding causes of aberrant responding. Simulated data analysis showed that the person-fit methods had good detection rates for substantially misfitting item-score vectors. Real-data person-fit analyses identified 4% to 17% misfitting item-score vectors. Removal of these vectors little improved model fit and test-score validity. The person-fit methods helped to understand causes of aberrant responding after controlling for response style on the explanatory variables. More real-data analyses are needed to demonstrate the usefulness of multiscale person-fit methods for noncognitive multiscale measures.
Keywords: aberrant response behavior, lz person-fit statistic, multiscale person-fit analysis, personality measurement
Original languageEnglish
Pages (from-to)122-136
JournalApplied Psychological Measurement
Volume38
DOIs
Publication statusPublished - 2014

Fingerprint

statistics
human being
personality
cause
response behavior
psychopathology
research results
data analysis
simulation

Cite this

Conijn, J.M. ; Emons, W.H.M. ; Sijtsma, K. / Statistic lz based person-fit methods for non-cognitive multiscale measures. In: Applied Psychological Measurement. 2014 ; Vol. 38. pp. 122-136.
@article{b47f417ee23a48929fa2036bd36755fe,
title = "Statistic lz based person-fit methods for non-cognitive multiscale measures",
abstract = "Most person-fit statistics require long tests to reliably detect aberrant item-score vectors and are not readily applicable to noncognitive measures that consist of multiple short subscales. The authors propose combining subscale person-fit information to detect aberrant item-score vectors on noncognitive multiscale measures. They used a simulation study and three empirical personality and psychopathology test datasets to assess five multiscale person-fit methods based on the lz person-fit statistic with respect to (a) identifying aberrant item-score vectors, (b) improving accuracy of research results, and (c) understanding causes of aberrant responding. Simulated data analysis showed that the person-fit methods had good detection rates for substantially misfitting item-score vectors. Real-data person-fit analyses identified 4{\%} to 17{\%} misfitting item-score vectors. Removal of these vectors little improved model fit and test-score validity. The person-fit methods helped to understand causes of aberrant responding after controlling for response style on the explanatory variables. More real-data analyses are needed to demonstrate the usefulness of multiscale person-fit methods for noncognitive multiscale measures.Keywords: aberrant response behavior, lz person-fit statistic, multiscale person-fit analysis, personality measurement",
author = "J.M. Conijn and W.H.M. Emons and K. Sijtsma",
year = "2014",
doi = "10.1177/0146621613497568",
language = "English",
volume = "38",
pages = "122--136",
journal = "Applied Psychological Measurement",
issn = "0146-6216",
publisher = "SAGE Publications Inc.",

}

Statistic lz based person-fit methods for non-cognitive multiscale measures. / Conijn, J.M.; Emons, W.H.M.; Sijtsma, K.

In: Applied Psychological Measurement, Vol. 38, 2014, p. 122-136.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Statistic lz based person-fit methods for non-cognitive multiscale measures

AU - Conijn, J.M.

AU - Emons, W.H.M.

AU - Sijtsma, K.

PY - 2014

Y1 - 2014

N2 - Most person-fit statistics require long tests to reliably detect aberrant item-score vectors and are not readily applicable to noncognitive measures that consist of multiple short subscales. The authors propose combining subscale person-fit information to detect aberrant item-score vectors on noncognitive multiscale measures. They used a simulation study and three empirical personality and psychopathology test datasets to assess five multiscale person-fit methods based on the lz person-fit statistic with respect to (a) identifying aberrant item-score vectors, (b) improving accuracy of research results, and (c) understanding causes of aberrant responding. Simulated data analysis showed that the person-fit methods had good detection rates for substantially misfitting item-score vectors. Real-data person-fit analyses identified 4% to 17% misfitting item-score vectors. Removal of these vectors little improved model fit and test-score validity. The person-fit methods helped to understand causes of aberrant responding after controlling for response style on the explanatory variables. More real-data analyses are needed to demonstrate the usefulness of multiscale person-fit methods for noncognitive multiscale measures.Keywords: aberrant response behavior, lz person-fit statistic, multiscale person-fit analysis, personality measurement

AB - Most person-fit statistics require long tests to reliably detect aberrant item-score vectors and are not readily applicable to noncognitive measures that consist of multiple short subscales. The authors propose combining subscale person-fit information to detect aberrant item-score vectors on noncognitive multiscale measures. They used a simulation study and three empirical personality and psychopathology test datasets to assess five multiscale person-fit methods based on the lz person-fit statistic with respect to (a) identifying aberrant item-score vectors, (b) improving accuracy of research results, and (c) understanding causes of aberrant responding. Simulated data analysis showed that the person-fit methods had good detection rates for substantially misfitting item-score vectors. Real-data person-fit analyses identified 4% to 17% misfitting item-score vectors. Removal of these vectors little improved model fit and test-score validity. The person-fit methods helped to understand causes of aberrant responding after controlling for response style on the explanatory variables. More real-data analyses are needed to demonstrate the usefulness of multiscale person-fit methods for noncognitive multiscale measures.Keywords: aberrant response behavior, lz person-fit statistic, multiscale person-fit analysis, personality measurement

U2 - 10.1177/0146621613497568

DO - 10.1177/0146621613497568

M3 - Article

VL - 38

SP - 122

EP - 136

JO - Applied Psychological Measurement

JF - Applied Psychological Measurement

SN - 0146-6216

ER -