Latent Variable Modelling and Item Response Theory Analyses in Marketing Research

• Main Author: Brzezińska Justyna
• Format: Article
• Language: English
• Published: Sciendo 2016-12-01
• Series: Folia Oeconomica Stetinensia
• Subjects: latent class analysis; latent variables; item response theory models; survey discrete survey response data; r software; c25; c51; c59
• Online Access: https://doi.org/10.1515/foli-2016-0032

Item Response Theory (IRT) is a modern statistical method using latent variables designed to model the interaction between a subject’s ability and the item level stimuli (difficulty, guessing). Item responses are treated as the outcome (dependent) variables, and the examinee’s ability and the items’ characteristics are the latent predictor (independent) variables. IRT models the relationship between a respondent’s trait (ability, attitude) and the pattern of item responses. Thus, the estimation of individual latent traits can differ even for two individuals with the same total scores. IRT scores can yield additional benefits and this will be discussed in detail. In this paper theory and application with R software with the use of packages designed for modelling IRT will be presented.