Item Response Theory

Abstract

Item response theory (IRT) is an increasingly popular approach to the development, evaluation, and administration of psychological measures. We introduce, first, three IRT fundamentals: (a) item response functions, (b) information functions, and (c) invariance. We next illustrate how IRT modeling can improve the quality of psychological measurement. Available evidence suggests that the differences between IRT and traditional psychometric methods are not trivial; IRT applications can improve the precision and validity of psychological research across a wide range of subjects.

Scale validation in applied health research: tutorial for a 6-step R-based psychometrics protocol

“…First, accounting for item difficulties results in less biased and more parsimonious estimations of dimensionality compared to FA (Schuur, 2003). Second, since persons and items have their independent locations on this dimension, IRT offers a major advantage compared to FA -the possibility of sample and item-independent measurement, and thus adaptive testing: given a larger item bank, each respondent may have to answer fewer items depending on their responses, resulting in lower respondent burden with equal or improved accuracy (Reise, Ainsworth, & Haviland, 2005). And third, it allows measure developers to maintain the width of the latent continuum (i.e.…”

Testing whether posttraumatic stress disorder and major depressive disorder are similar or unique constructs

“…Rasch modeling fits an equation that best characterizes the probability of endorsing an item (Reise & Henson, 2003) (e.g., a PTSD symptom). The model is a monotonically increasing function -the probability of item endorsement increases as the latent, unobserved trait level increases (Reise, Ainsworth, & Haviland, 2005) -and a person can be described as having a specific location on a continuous trait dimension (Embretson, 2006). Rasch analysis assumes that items are uncorrelated with each other, after controlling for the latent trait (Embretson, 2006).…”

The burden of social proof: Shared thresholds and social influence.

“…The logistic threshold models I propose in this article share features with item-response models in psychometrics (Birnbaum, 1968;De Boeck, Wilson, & Acton, 2005;Reise et al, 2005), as well as discrete choice models in psychology (Augustin, 2005;Luce, 1959), economics (McFadden, 1974(McFadden, , 2001, and sociology (Macy, 1991). But not all logistical models are threshold models, and the threshold models presented here do not require the logistic function.…”

“…Kimble (1996) identified the concept of thresholds as one of a handful of bedrock principles belonging at the core of a unified scientific psychology. In some areas of psychology, we make routine use of thresholds to interpret data; examples include statistical significance testing (e.g., Cohen, 1994), signal detection theory (e.g., Swets, 1988), dose-response functions in pharmacology (Berkson, 1944), and item-response theory in testing (e.g., Reise, Ainsworth, & Haviland, 2005). But psychologists have made more use of threshold concepts to explain perception and judgment than to explain social behavior.…”