Some pitfalls in the use of factor scores: The case of the Kirton adaption-innovation inventory

Abstract

The use of factor analysis to generate scores on composite scales has some psychometric appeal as it allows for the partition of item variance. However, two major issues make such procedures problematic. The first concerns generalizing factor score weights from one sample to another and is essentially the problem of factor invariance. The second issue concerns the psychometric problem of factor indeterminacy. Mulligan and Martin have advocated the use of factor scores with the increasingly widely used Kirton Adaption-Innovation Inventory (KAI). This paper discusses the pitfalls of using factor scores in general and then investigates empirically whether Mulligan and Martin's proposal is justified with the KAI using an Irish sample. It is concluded that the summated rating method of scoring the KAI is superior to the factor-analytic procedure.