A Semiparametric Approach for Modeling Not-Reached Items

Research output: Journal contributionsJournal articlesResearchpeer-review

Standard

A Semiparametric Approach for Modeling Not-Reached Items. / List, Marit Kristine; Köller, Olaf; Nagy, Gabriel.
In: Educational and Psychological Measurement, Vol. 79, No. 1, 01.02.2019, p. 170-199.

Research output: Journal contributionsJournal articlesResearchpeer-review

Harvard

APA

Vancouver

List MK, Köller O, Nagy G. A Semiparametric Approach for Modeling Not-Reached Items. Educational and Psychological Measurement. 2019 Feb 1;79(1):170-199. doi: 10.1177/0013164417749679

Bibtex

@article{001719c5123943499599893be4cbda84,
title = "A Semiparametric Approach for Modeling Not-Reached Items",
abstract = "Tests administered in studies of student achievement often have a certain amount of not-reached items (NRIs). The propensity for NRIs may depend on the proficiency measured by the test and on additional covariates. This article proposes a semiparametric model to study such relationships. Our model extends Glas and Pimentel{\textquoteright}s item response theory model for NRIs by (1) including a semiparametric representation of the distribution of the onset of NRIs, (2) modeling the relationships of NRIs with proficiency via a flexible multinomial logit regression, and (3) including additional covariates to predict NRIs. We show that Glas and Pimentel{\textquoteright}s and our model have close connections to event history analysis, thereby making it possible to apply tools developed in this context to the analysis of NRIs. Our model was applied to a timed low-stakes test of mathematics achievement. Our model fitted the data better than Glas and Pimentel{\textquoteright}s model, and allowed for a more fine-grained assessment of the onset of NRIs. The results of a simulation study showed that our model accurately recovered the relationships of proficiency and covariates with the onset of NRIs, and reduced bias in the estimates of item parameters, proficiency distributions, and covariate effects on proficiency.",
keywords = "educational assessment, event history analysis, item response theory, latent class analysis, nonlinear relations, not-reached items, Empirical education research, Educational science",
author = "List, {Marit Kristine} and Olaf K{\"o}ller and Gabriel Nagy",
note = "Publisher Copyright: {\textcopyright} The Author(s) 2017.",
year = "2019",
month = feb,
day = "1",
doi = "10.1177/0013164417749679",
language = "English",
volume = "79",
pages = "170--199",
journal = "Educational and Psychological Measurement",
issn = "0013-1644",
publisher = "SAGE Publications Inc.",
number = "1",

}

RIS

TY - JOUR

T1 - A Semiparametric Approach for Modeling Not-Reached Items

AU - List, Marit Kristine

AU - Köller, Olaf

AU - Nagy, Gabriel

N1 - Publisher Copyright: © The Author(s) 2017.

PY - 2019/2/1

Y1 - 2019/2/1

N2 - Tests administered in studies of student achievement often have a certain amount of not-reached items (NRIs). The propensity for NRIs may depend on the proficiency measured by the test and on additional covariates. This article proposes a semiparametric model to study such relationships. Our model extends Glas and Pimentel’s item response theory model for NRIs by (1) including a semiparametric representation of the distribution of the onset of NRIs, (2) modeling the relationships of NRIs with proficiency via a flexible multinomial logit regression, and (3) including additional covariates to predict NRIs. We show that Glas and Pimentel’s and our model have close connections to event history analysis, thereby making it possible to apply tools developed in this context to the analysis of NRIs. Our model was applied to a timed low-stakes test of mathematics achievement. Our model fitted the data better than Glas and Pimentel’s model, and allowed for a more fine-grained assessment of the onset of NRIs. The results of a simulation study showed that our model accurately recovered the relationships of proficiency and covariates with the onset of NRIs, and reduced bias in the estimates of item parameters, proficiency distributions, and covariate effects on proficiency.

AB - Tests administered in studies of student achievement often have a certain amount of not-reached items (NRIs). The propensity for NRIs may depend on the proficiency measured by the test and on additional covariates. This article proposes a semiparametric model to study such relationships. Our model extends Glas and Pimentel’s item response theory model for NRIs by (1) including a semiparametric representation of the distribution of the onset of NRIs, (2) modeling the relationships of NRIs with proficiency via a flexible multinomial logit regression, and (3) including additional covariates to predict NRIs. We show that Glas and Pimentel’s and our model have close connections to event history analysis, thereby making it possible to apply tools developed in this context to the analysis of NRIs. Our model was applied to a timed low-stakes test of mathematics achievement. Our model fitted the data better than Glas and Pimentel’s model, and allowed for a more fine-grained assessment of the onset of NRIs. The results of a simulation study showed that our model accurately recovered the relationships of proficiency and covariates with the onset of NRIs, and reduced bias in the estimates of item parameters, proficiency distributions, and covariate effects on proficiency.

KW - educational assessment

KW - event history analysis

KW - item response theory

KW - latent class analysis

KW - nonlinear relations

KW - not-reached items

KW - Empirical education research

KW - Educational science

UR - http://www.scopus.com/inward/record.url?scp=85043390035&partnerID=8YFLogxK

U2 - 10.1177/0013164417749679

DO - 10.1177/0013164417749679

M3 - Journal articles

AN - SCOPUS:85043390035

VL - 79

SP - 170

EP - 199

JO - Educational and Psychological Measurement

JF - Educational and Psychological Measurement

SN - 0013-1644

IS - 1

ER -

DOI