Understanding Rasch and Item Response Theory Models: Applications to the Estimation and Validation of Interval Latent Trait Measures from Responses to Rating Scale Questionnaires

Abstract

Background: Modern psychometric theory is now routinely used in clinical vision research, as well as other areas of health research, to measure latent health states on continuous interval scales from responses to self-report rating scale questionnaires. Two competing theories are commonly employed: Rasch theory and item response theory.

Methods: Because the field is currently in transition from using traditional scoring algorithms based on classical test theory to using the more modern approaches, this article offers a tutorial review of Rasch theory and item response theory and of the analytical methods employed by the two theories to estimate and validate measures.

KEYWORDS::

• Patient-reported outcome measure
• Visual function questionnaire
• Quality of life
• Self-report questionnaire
• Rasch analysis
• IRT
• Rating scale model
• Graded response model
• Partial credit model

Declaration of interest: This study was supported by grant EY-012045 from the National Eye Institute, National Institutes of Health; a grant from the Alcon Research Institute; and a grant from Research to Prevent Blindness.