Item response theory for weighted summed scores Public Deposited

Downloadable Content

Download PDF
Last Modified
  • March 21, 2019
  • Stucky, Brian Dale
    • Affiliation: College of Arts and Sciences, Department of Psychology and Neuroscience
  • Tests composed of multiple sections are routinely weighted by section. Methods for weighting have existed perhaps as long as there have been tests; however, computing and evaluating the quality of weights has not evolved with recent advances in test theory (Item Response Theory (IRT)). While IRT may be used to compute accurate estimates of ability based on a variety of information (e.g., pattern responses or summed scores), there has been little research on the computation of scale score estimates for tests with arbitrary item or test section weights. The present work provides an extension to a recursive algorithm for the computation of IRT-scale scores from weighted summed scores.
Date of publication
Resource type
Rights statement
  • In Copyright
  • Thissen, David
  • Open access

This work has no parents.