The identification of relevant attributes is the first objective of conjoint analysis. Today, as a result of technological development, it is common for researchers to use adaptive conjoint analysis (ACA) which combines different types of research (e.g. self-assessment questionnaires with an orthogonal design for experiments). ACA, based on partial profiles, is a flexible sequential model that tailors the experimental design to each respondent depending on their previously stated preferences ordered in the self-assessment questionnaire. However, many authors hold that the full profile offers more advantages than the partial one, because it develops a more realistic description of stimuli. Based on full profiles, this study proposes a new strategy to improve the performance of the second step of the ACA process. This strategy allows for estimations of main factors and two-factor interactions with the lowest number of profiles. Our proposal is based on the use of a full profile approach in which the profiles are arranged in two-level factorial designs in blocks of two, and the levels of each factor are codified in a vector manner. © 2012 Springer-Verlag Berlin Heidelberg.
CITATION STYLE
Huertas-García, R., Forgas-Coll, S., & Gázquez-Abad, J. C. (2012). A proposal for improving the performance of adaptive conjoint analysis. In Studies in Fuzziness and Soft Computing (Vol. 286, pp. 423–434). https://doi.org/10.1007/978-3-642-30457-6_28
Mendeley helps you to discover research relevant for your work.