Stepwise item selection procedures for Rasch scales using quasi-loglinear models

Dirk L. Knol

Research output: Book/ReportReportOther research output

6 Downloads (Pure)

Abstract

Two iterative procedures for constructing Rasch scales are presented. A log-likelihood ratio test based on a quasi-loglinear formulation of the Rasch model is given by which one item at a time can be deleted from or added to an initial item set. In the so-called "top-down" algorithm, items are stepwise deleted from a relatively large initial item set, whereas in the "bottom-up" algorithm items are stepwise added to a relatively small initial item set. Both algorithms are evaluated through a simulation study with generated data. Item parameters are given for four generated unidimensional data sets and two generated two-dimensional sets. Abilities were randomly sampled from a multivariate normal distribution with a sample size of 1,000. Results for the top-down algorithm were poor, but results for the bottom-up algorithm were more encouraging. It is suggested that alternating the bottom-up algorithm with one or two iterations of the top-down algorithm would allow the procedure to reject items that were added incorrectly in a previous step.
Original languageUndefined
Place of PublicationEnschede, the Netherlands
PublisherUniversity of Twente, Faculty Educational Science and Technology
Publication statusPublished - 1989

Publication series

NameOMD research report
PublisherUniversity of Twente, Faculty of Educational Science and Technology
No.89-3

Keywords

  • Latent Trait Theory
  • Test Construction
  • Test Items
  • Item Banks
  • Simulation
  • Mathematical Models
  • Statistical Analysis
  • Algorithms
  • Measures (Individuals)
  • IR-104187
  • Selection

Cite this

Knol, D. L. (1989). Stepwise item selection procedures for Rasch scales using quasi-loglinear models. (OMD research report; No. 89-3). Enschede, the Netherlands: University of Twente, Faculty Educational Science and Technology.
Knol, Dirk L. / Stepwise item selection procedures for Rasch scales using quasi-loglinear models. Enschede, the Netherlands : University of Twente, Faculty Educational Science and Technology, 1989. (OMD research report; 89-3).
@book{dc4dfaed693746e3be215a8f4b9d1901,
title = "Stepwise item selection procedures for Rasch scales using quasi-loglinear models",
abstract = "Two iterative procedures for constructing Rasch scales are presented. A log-likelihood ratio test based on a quasi-loglinear formulation of the Rasch model is given by which one item at a time can be deleted from or added to an initial item set. In the so-called {"}top-down{"} algorithm, items are stepwise deleted from a relatively large initial item set, whereas in the {"}bottom-up{"} algorithm items are stepwise added to a relatively small initial item set. Both algorithms are evaluated through a simulation study with generated data. Item parameters are given for four generated unidimensional data sets and two generated two-dimensional sets. Abilities were randomly sampled from a multivariate normal distribution with a sample size of 1,000. Results for the top-down algorithm were poor, but results for the bottom-up algorithm were more encouraging. It is suggested that alternating the bottom-up algorithm with one or two iterations of the top-down algorithm would allow the procedure to reject items that were added incorrectly in a previous step.",
keywords = "Latent Trait Theory, Test Construction, Test Items, Item Banks, Simulation, Mathematical Models, Statistical Analysis, Algorithms, Measures (Individuals), IR-104187, Selection",
author = "Knol, {Dirk L.}",
note = "Project Psychometric Aspects of Item Banking No. 44",
year = "1989",
language = "Undefined",
series = "OMD research report",
publisher = "University of Twente, Faculty Educational Science and Technology",
number = "89-3",

}

Knol, DL 1989, Stepwise item selection procedures for Rasch scales using quasi-loglinear models. OMD research report, no. 89-3, University of Twente, Faculty Educational Science and Technology, Enschede, the Netherlands.

Stepwise item selection procedures for Rasch scales using quasi-loglinear models. / Knol, Dirk L.

Enschede, the Netherlands : University of Twente, Faculty Educational Science and Technology, 1989. (OMD research report; No. 89-3).

Research output: Book/ReportReportOther research output

TY - BOOK

T1 - Stepwise item selection procedures for Rasch scales using quasi-loglinear models

AU - Knol, Dirk L.

N1 - Project Psychometric Aspects of Item Banking No. 44

PY - 1989

Y1 - 1989

N2 - Two iterative procedures for constructing Rasch scales are presented. A log-likelihood ratio test based on a quasi-loglinear formulation of the Rasch model is given by which one item at a time can be deleted from or added to an initial item set. In the so-called "top-down" algorithm, items are stepwise deleted from a relatively large initial item set, whereas in the "bottom-up" algorithm items are stepwise added to a relatively small initial item set. Both algorithms are evaluated through a simulation study with generated data. Item parameters are given for four generated unidimensional data sets and two generated two-dimensional sets. Abilities were randomly sampled from a multivariate normal distribution with a sample size of 1,000. Results for the top-down algorithm were poor, but results for the bottom-up algorithm were more encouraging. It is suggested that alternating the bottom-up algorithm with one or two iterations of the top-down algorithm would allow the procedure to reject items that were added incorrectly in a previous step.

AB - Two iterative procedures for constructing Rasch scales are presented. A log-likelihood ratio test based on a quasi-loglinear formulation of the Rasch model is given by which one item at a time can be deleted from or added to an initial item set. In the so-called "top-down" algorithm, items are stepwise deleted from a relatively large initial item set, whereas in the "bottom-up" algorithm items are stepwise added to a relatively small initial item set. Both algorithms are evaluated through a simulation study with generated data. Item parameters are given for four generated unidimensional data sets and two generated two-dimensional sets. Abilities were randomly sampled from a multivariate normal distribution with a sample size of 1,000. Results for the top-down algorithm were poor, but results for the bottom-up algorithm were more encouraging. It is suggested that alternating the bottom-up algorithm with one or two iterations of the top-down algorithm would allow the procedure to reject items that were added incorrectly in a previous step.

KW - Latent Trait Theory

KW - Test Construction

KW - Test Items

KW - Item Banks

KW - Simulation

KW - Mathematical Models

KW - Statistical Analysis

KW - Algorithms

KW - Measures (Individuals)

KW - IR-104187

KW - Selection

M3 - Report

T3 - OMD research report

BT - Stepwise item selection procedures for Rasch scales using quasi-loglinear models

PB - University of Twente, Faculty Educational Science and Technology

CY - Enschede, the Netherlands

ER -

Knol DL. Stepwise item selection procedures for Rasch scales using quasi-loglinear models. Enschede, the Netherlands: University of Twente, Faculty Educational Science and Technology, 1989. (OMD research report; 89-3).