A simple and fast item selection procedure for adaptive testing

W.J.J. Veerkamp, Wim J.J. Veerkamp, Martijn Berger, Martijn P.F. Berger

Research output: Book/ReportReportProfessional

11 Downloads (Pure)

Abstract

Items with the highest discrimination parameter values in a logistic item response theory (IRT) model do not necessarily give maximum information. This paper shows which discrimination parameter values (as a function of the guessing parameter and the distance between person ability and item difficulty) give maximum information for the three-parameter logistic IRT model. The optimal discrimination parameter value is shown to be inversely related to the distance between item difficulty and person ability. An upper bound for the information as a function of these parameters is derived; and this upper bound is used to formulate a fast item selection algorithm for adaptive testing. In a small simulation study this algorithm was one and one half to six times as fast as an algorithm in which the information of all items in an item bank is calculated.
Original languageEnglish
Place of PublicationEnschede
PublisherUniversity of Twente, Faculty Educational Science and Technology
Number of pages25
Publication statusPublished - 1994

Publication series

NameOMD research report
PublisherUniversity of Twente, Faculty of Educational Science and Technology
No.94-13

Fingerprint

Adaptive Testing
Selection Procedures
Discrimination
Model Theory
Logistics
Person
Upper bound
Simulation Study

Keywords

  • Item Banks
  • Adaptive Testing
  • Test Items
  • Computer Assisted Testing
  • Models
  • Algorithms
  • Difficulty Level
  • Guessing (Tests)
  • Simulation
  • Item Response Theory
  • Selection
  • METIS-140142
  • IR-104215
  • Ability
  • Test Construction

Cite this

Veerkamp, W. J. J., Veerkamp, W. J. J., Berger, M., & Berger, M. P. F. (1994). A simple and fast item selection procedure for adaptive testing. (OMD research report; No. 94-13). Enschede: University of Twente, Faculty Educational Science and Technology.
Veerkamp, W.J.J. ; Veerkamp, Wim J.J. ; Berger, Martijn ; Berger, Martijn P.F. / A simple and fast item selection procedure for adaptive testing. Enschede : University of Twente, Faculty Educational Science and Technology, 1994. 25 p. (OMD research report; 94-13).
@book{82c285fa9c204d819a7749ee2cc1160d,
title = "A simple and fast item selection procedure for adaptive testing",
abstract = "Items with the highest discrimination parameter values in a logistic item response theory (IRT) model do not necessarily give maximum information. This paper shows which discrimination parameter values (as a function of the guessing parameter and the distance between person ability and item difficulty) give maximum information for the three-parameter logistic IRT model. The optimal discrimination parameter value is shown to be inversely related to the distance between item difficulty and person ability. An upper bound for the information as a function of these parameters is derived; and this upper bound is used to formulate a fast item selection algorithm for adaptive testing. In a small simulation study this algorithm was one and one half to six times as fast as an algorithm in which the information of all items in an item bank is calculated.",
keywords = "Item Banks, Adaptive Testing, Test Items, Computer Assisted Testing, Models, Algorithms, Difficulty Level, Guessing (Tests), Simulation, Item Response Theory, Selection, METIS-140142, IR-104215, Ability, Test Construction",
author = "W.J.J. Veerkamp and Veerkamp, {Wim J.J.} and Martijn Berger and Berger, {Martijn P.F.}",
year = "1994",
language = "English",
series = "OMD research report",
publisher = "University of Twente, Faculty Educational Science and Technology",
number = "94-13",

}

Veerkamp, WJJ, Veerkamp, WJJ, Berger, M & Berger, MPF 1994, A simple and fast item selection procedure for adaptive testing. OMD research report, no. 94-13, University of Twente, Faculty Educational Science and Technology, Enschede.

A simple and fast item selection procedure for adaptive testing. / Veerkamp, W.J.J.; Veerkamp, Wim J.J.; Berger, Martijn; Berger, Martijn P.F.

Enschede : University of Twente, Faculty Educational Science and Technology, 1994. 25 p. (OMD research report; No. 94-13).

Research output: Book/ReportReportProfessional

TY - BOOK

T1 - A simple and fast item selection procedure for adaptive testing

AU - Veerkamp, W.J.J.

AU - Veerkamp, Wim J.J.

AU - Berger, Martijn

AU - Berger, Martijn P.F.

PY - 1994

Y1 - 1994

N2 - Items with the highest discrimination parameter values in a logistic item response theory (IRT) model do not necessarily give maximum information. This paper shows which discrimination parameter values (as a function of the guessing parameter and the distance between person ability and item difficulty) give maximum information for the three-parameter logistic IRT model. The optimal discrimination parameter value is shown to be inversely related to the distance between item difficulty and person ability. An upper bound for the information as a function of these parameters is derived; and this upper bound is used to formulate a fast item selection algorithm for adaptive testing. In a small simulation study this algorithm was one and one half to six times as fast as an algorithm in which the information of all items in an item bank is calculated.

AB - Items with the highest discrimination parameter values in a logistic item response theory (IRT) model do not necessarily give maximum information. This paper shows which discrimination parameter values (as a function of the guessing parameter and the distance between person ability and item difficulty) give maximum information for the three-parameter logistic IRT model. The optimal discrimination parameter value is shown to be inversely related to the distance between item difficulty and person ability. An upper bound for the information as a function of these parameters is derived; and this upper bound is used to formulate a fast item selection algorithm for adaptive testing. In a small simulation study this algorithm was one and one half to six times as fast as an algorithm in which the information of all items in an item bank is calculated.

KW - Item Banks

KW - Adaptive Testing

KW - Test Items

KW - Computer Assisted Testing

KW - Models

KW - Algorithms

KW - Difficulty Level

KW - Guessing (Tests)

KW - Simulation

KW - Item Response Theory

KW - Selection

KW - METIS-140142

KW - IR-104215

KW - Ability

KW - Test Construction

M3 - Report

T3 - OMD research report

BT - A simple and fast item selection procedure for adaptive testing

PB - University of Twente, Faculty Educational Science and Technology

CY - Enschede

ER -

Veerkamp WJJ, Veerkamp WJJ, Berger M, Berger MPF. A simple and fast item selection procedure for adaptive testing. Enschede: University of Twente, Faculty Educational Science and Technology, 1994. 25 p. (OMD research report; 94-13).