An Item Response Theory Model for Incorporating Response Time Data in Binary Personality Items

Abstract

This article describes a general item response theory model for personality items that allows the information provided by the item response times to be used to estimate the individual trait levels. The submodel describing the item response times is a modification of Thissen's log-linear model and is based on the distance-difficulty hypothesis in personality measurement. First, the procedures for fitting the model and assessing the goodness of fit are described. Second, the gain in the precision of estimating the individual trait levels when the information provided by the response times is used is assessed. Finally, all the developments in this article are illustrated by means of an empirical example.