Statistical methods in Kansei engineering: a case of statistical engineering

Abstract

Kansei engineering (KE) is a methodology used to incorporate emotions in products and services design. Its basic purpose is discovering in which way some properties of a product or a service convey certain emotions in its users. Data are typically collected using questionnaires. KE studies follow a model with three main steps: (i) defining the elicited emotions (semantic space); (ii) deciding on the factors that might affect the responses (space of properties); and (iii) modeling how each factor affects each response (synthesis phase). The procedure resembles that of an experimental design in an industrial context. However, practitioners of KE are hardly ever statisticians. Statistical techniques in KE are sometimes misused, and the discipline could benefit from a more extensive use of statistical methods. KE is thus a good area of application of statistical engineering: focusing not in advancement of statistics but on how current techniques can be best used in a new area. The aim of this paper is twofold: (i) to present the fundamentals of KE while giving an easy to understand example to illustrate the procedure; and (ii) to explain why KE is a good example of statistical engineering by proposing improvements that emanate from the adequate use of statistical techniques.