作者: Felix Eggers , Henrik Sattler
DOI: 10.1016/J.IJRESMAR.2009.01.002
关键词: Empirical research 、 Conjoint analysis 、 Flexibility (engineering) 、 Preference (economics) 、 Econometrics 、 Price level 、 Economics 、 Artificial intelligence 、 Predictive validity 、 Willingness to pay 、 Machine learning 、 Transformation (function)
摘要: Abstract The authors introduce hybrid individualized two-level choice-based conjoint (HIT-CBC), which combines self-explicated preference measurement (SE) with analysis (CBC). CBC part is adapted individually to a choice design that uses only the best and worst levels of each attribute identified in SE phase. Prior knowledge about allows HIT-CBC generate an adaptive efficient (i.e., Pareto-optimal, balanced, orthogonal, minimally overlapping) easy implement. Whereas existing approaches suffer from number-of-levels effect, avoids this problem because it reduces every two levels. Thus, appropriate for problems many imbalanced Furthermore, transformation exemplifies new favorable way account consumer heterogeneity. In addition, introduces possibility using willingness-to-pay measures as price levels, results more flexibility modeling demand functions (e.g., identifying thresholds). A simulation study empirical show robust predictive validity compared standard approach, illustrate advantages pricing study.