Minimizing the testlet effect: Identifying critical testlet features by means of tree-based regression

Muirne Paap, Bernard P. Veldkamp

Research output: Chapter in Book/Report/Conference proceedingChapterAcademic

111 Downloads (Pure)

Abstract

Standardized tests often group items around a common stimulus. Such groupings of items are called testlets. The potential dependency among items within a testlet is generally ignored in practice, even though a basic assumption of item response theory (IRT) is that individual items are independent of one another. A technique called tree-based regression (TBR) was applied to identify key features of stimuli that could properly predict the dependence structure of testlet data. Knowledge about these features might help to develop item sets with small testlet effects. This study illustrates the merits of TBR in the analysis of test data.
Original languageEnglish
Title of host publicationPsychometrics in practice at RCEC
EditorsT.J.H.M. Eggen, B.P. Veldkamp
Place of PublicationEnschede
PublisherRCEC
Pages74-83
Number of pages180
ISBN (Print)9789036533744
DOIs
Publication statusPublished - 2012

Publication series

Name
PublisherRCEC

Fingerprint

stimulus
regression
grouping
Group

Keywords

  • METIS-291466
  • IR-80207

Cite this

Paap, M., & Veldkamp, B. P. (2012). Minimizing the testlet effect: Identifying critical testlet features by means of tree-based regression. In T. J. H. M. Eggen, & B. P. Veldkamp (Eds.), Psychometrics in practice at RCEC (pp. 74-83). Enschede: RCEC. https://doi.org/10.3990/3.9789036533744
Paap, Muirne ; Veldkamp, Bernard P. / Minimizing the testlet effect: Identifying critical testlet features by means of tree-based regression. Psychometrics in practice at RCEC. editor / T.J.H.M. Eggen ; B.P. Veldkamp. Enschede : RCEC, 2012. pp. 74-83
@inbook{71b2392689524112ba245c7a4b3f724d,
title = "Minimizing the testlet effect: Identifying critical testlet features by means of tree-based regression",
abstract = "Standardized tests often group items around a common stimulus. Such groupings of items are called testlets. The potential dependency among items within a testlet is generally ignored in practice, even though a basic assumption of item response theory (IRT) is that individual items are independent of one another. A technique called tree-based regression (TBR) was applied to identify key features of stimuli that could properly predict the dependence structure of testlet data. Knowledge about these features might help to develop item sets with small testlet effects. This study illustrates the merits of TBR in the analysis of test data.",
keywords = "METIS-291466, IR-80207",
author = "Muirne Paap and Veldkamp, {Bernard P.}",
year = "2012",
doi = "10.3990/3.9789036533744",
language = "English",
isbn = "9789036533744",
publisher = "RCEC",
pages = "74--83",
editor = "T.J.H.M. Eggen and B.P. Veldkamp",
booktitle = "Psychometrics in practice at RCEC",

}

Paap, M & Veldkamp, BP 2012, Minimizing the testlet effect: Identifying critical testlet features by means of tree-based regression. in TJHM Eggen & BP Veldkamp (eds), Psychometrics in practice at RCEC. RCEC, Enschede, pp. 74-83. https://doi.org/10.3990/3.9789036533744

Minimizing the testlet effect: Identifying critical testlet features by means of tree-based regression. / Paap, Muirne; Veldkamp, Bernard P.

Psychometrics in practice at RCEC. ed. / T.J.H.M. Eggen; B.P. Veldkamp. Enschede : RCEC, 2012. p. 74-83.

Research output: Chapter in Book/Report/Conference proceedingChapterAcademic

TY - CHAP

T1 - Minimizing the testlet effect: Identifying critical testlet features by means of tree-based regression

AU - Paap, Muirne

AU - Veldkamp, Bernard P.

PY - 2012

Y1 - 2012

N2 - Standardized tests often group items around a common stimulus. Such groupings of items are called testlets. The potential dependency among items within a testlet is generally ignored in practice, even though a basic assumption of item response theory (IRT) is that individual items are independent of one another. A technique called tree-based regression (TBR) was applied to identify key features of stimuli that could properly predict the dependence structure of testlet data. Knowledge about these features might help to develop item sets with small testlet effects. This study illustrates the merits of TBR in the analysis of test data.

AB - Standardized tests often group items around a common stimulus. Such groupings of items are called testlets. The potential dependency among items within a testlet is generally ignored in practice, even though a basic assumption of item response theory (IRT) is that individual items are independent of one another. A technique called tree-based regression (TBR) was applied to identify key features of stimuli that could properly predict the dependence structure of testlet data. Knowledge about these features might help to develop item sets with small testlet effects. This study illustrates the merits of TBR in the analysis of test data.

KW - METIS-291466

KW - IR-80207

U2 - 10.3990/3.9789036533744

DO - 10.3990/3.9789036533744

M3 - Chapter

SN - 9789036533744

SP - 74

EP - 83

BT - Psychometrics in practice at RCEC

A2 - Eggen, T.J.H.M.

A2 - Veldkamp, B.P.

PB - RCEC

CY - Enschede

ER -

Paap M, Veldkamp BP. Minimizing the testlet effect: Identifying critical testlet features by means of tree-based regression. In Eggen TJHM, Veldkamp BP, editors, Psychometrics in practice at RCEC. Enschede: RCEC. 2012. p. 74-83 https://doi.org/10.3990/3.9789036533744