Measuring customer preferences in new product development: comparing compositional and decompositional methods

Abstract

Preference measurement is important in the early stages of new product development. Conjoint analysis (CA) and analytic hierarchy process (AHP) are common methods for measuring preferences with CA dominating marketing research and practice. These methods mainly differ with respect to their basic conception: AHP is a compositional method whereas CA is designed in a decompositional manner. This study aims at comparing the methods as instruments of preference measurement. The results show a high degree of predictive and convergent validity of both methods. However, inspecting the results in detail reveals considerable differences, which indicate that AHP performs slightly better.