Abstract:
A present research investigated if an IRT-scored forced-choice personality questionnaire has the same normative data structures as a similar version that uses a 5-point Likert scale instead. The study was conducted using a sample of 349 training delegates who completed both an IRT-scored forced-choice and a normative single stimulus version of the questionnaire. Results largely supported the scaling properties, measurements precision and equivalence of the data structures of the two scoring methods.
