Conjoint analysis with mixed levels of attributes

Abstract

Purpose The conjoint analyst in marketing are interested in detecting whether there exist synergy or antago-nistic effects between two attributes. In the cases where attributes have two or three levels, we research on the design of survey questionnaire to estimate all the main effect and as many two factor interaction effects as possible. Methods We consider the balanced incomplete block (BIB) mixed level factorial design 2f × 3g or fractional factorial design. To reduce the number of questions in a questionnaire, we propose the balanced incomplete block mixed level design with minimum aberration which is generated by implementing proc factex in SAS. Also, we propose using two or three level BIB factorial design instead of mixed level designs by transforming three level attributes into two attributes of two levels and two level attribute into three level attribute by using dummy level technique. Results We propose three methods for designing survey questionnaire where the block and design generators are found with practical number of questions in a questionnaire. By analyzing all the respondents survey data generated by the simulation study, we find the proper model and do the concepts optimization. Conclusion The proposed methods of designing survey questionnaires seem to perform well in the sense that the proper model, and then the optimal concept is found in a case study where all the respondents survey data are generated by the simulation study. Key words: Conjoint Analysis, BIB Mixed Level Factorial Design, BIB Factorial Design, Concepts Optimization