Dimensionality, Scoring, and Related Problems in Adaptive Testing.

Abstract

Major efforts of the project fall into four categories: Investigations were performed on the relationship between the dimensionality of a dataset and its underlying cognitive processes. Two approaches for diagnosing erroneous rules of operation were developed; an 'error vector' system for constructing error diagnostic programs for signed-number arithmetic and fraction addition problems, and a series of logical statements for constructing diagnostic programs for fraction problems; To circumvent the problems encountered in the construction of error diagnostic programs, two indices based on deterministic Guttman theory were formed and used to detect aberrant response patterns; and The necessity for dealing quantitatively with variations in errors and changing rules of operation led to the investigation of probabalistic models for error diagnosis based on item response theory.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1984
Accession Number
ADA139849

Entities

People

  • J. M. Eddins
  • K. Tatsuoka
  • M. Tatsuoka

Organizations

  • University of Illinois Urbana–Champaign

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Achievement Tests
  • Algorithms
  • Applied Psychology
  • Biological Sciences
  • California
  • Cognition
  • Conformity
  • Data Sets
  • Educational Psychology
  • Error Analysis
  • Illinois
  • Military Research
  • New England
  • Psychology
  • Students
  • United States
  • United States Government

Readers

  • Artificial Intelligence
  • Psychometric Testing or Psychological Assessment.
  • Theoretical Analysis.