Progress in Characterizing Strictly Unidimensional IRT Representations

Abstract

Item response theory, IRT, is a modern attempt to model-and statistically analyze-examinee responses on standardized achievement or aptitude tests. IRT modeling and analysis, which occurs at the level of individual test questions-item-is greatly facilitated by the assumption of unidimensionality, i. e. that the latent trait driving the item responses is a one-dimensional, typically real-valued, random variable. Birnbaum (1968) and Lord (1980) provide complete accounts of traditional unidimensional IRT. In this paper we are concerned with general characterization of (the distributions of) item response data for which traditional unidimensional IRT representations exist. For our purposes, a test is simply a vector of J items, or equivalently J binary (0/1) item response variables representing the correctness of responses of a randomly- chosen examinee to the J test items.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 29, 1990
Accession Number
ADA229993

Entities

People

  • Brian W. Junker

Organizations

  • University of Illinois Urbana–Champaign

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • California
  • Classification
  • Education
  • Educational Psychology
  • Illinois
  • Military Research
  • New England
  • New York
  • Probability
  • Psychological Tests
  • Psychology
  • Random Variables
  • Security
  • Simulations
  • South Carolina
  • Statistical Tests
  • United States

Fields of Study

  • Mathematics

Readers

  • Mathematical Modeling and Probability Theory.
  • Psychometric Testing or Psychological Assessment.