An introduction to item response theory and Rasch models for speech-language pathologists

To present a primarily conceptual introduction to item response theory (IRT) and Rasch models for speech-language pathologists (SLPs).

This tutorial introduces SLPs to basic concepts and terminology related to IRT as well as the most common IRT models. The article then continues with an overview of how instruments are developed using IRT and some basic principles of adaptive testing.

IRT is a set of statistical methods that are increasingly used for developing instruments in speech-language pathology. While IRT is not new, its application in speech-language pathology to date has been relatively limited in scope. Several new IRT-based instruments are currently emerging. IRT differs from traditional methods for test development, typically referred to as classical test theory (CTT), in several theoretical and practical ways. Administration, scoring, and interpretation of IRT instruments are different from methods used for most traditional CTT instruments. SLPs will need to understand the basic concepts of IRT instruments to use these tools in their clinical and research work. This article provides an introduction to IRT concepts drawing on examples from speech-language pathology.