A Comparison of Adaptive Choice‐Based Conjoint and Choice‐Based Conjoint to Determine Key Choice Attributes of Sour Cream with Limited Sample Size

Abstract

AbstractAdaptive choice‐based conjoint (ACBC) analysis is a technique that uses choice data and incorporates it into an adaptive interviewing experience. ACBC analysis has been suggested to provide more accurate information at the individual level, which can lead to better predictions even when using smaller sample sizes. A comparison of a traditional choice‐based conjoint (CBC) survey and an ACBC survey was undertaken to compare the overall utility scores and importance values of attributes determined by both techniques using sour cream as the subject. A CBC and an ACBC survey were conducted. More respondents participated in the CBC (n = 777) survey than in the ACBC version (n = 250). Respondents to the ACBC version were from the same pool of respondents to the CBC version. A random sample of 250 respondents from the CBC survey was also analyzed. Results were analyzed by overall utility scores, importance values, landscape segmentation analysis and cluster analysis via latent class. The ACBC and CBC results were similar in overall utility scores for all attributes with similar respondent clusters. Both techniques revealed fat content as the most important attribute, followed by price and followed by brand. The CBC result for 250 respondents overestimated the importance of brand. The ACBC utility scores were not as distinct as CBC results in all categories; however, the direction of the mean utility scores was the same in all categories. Overall, ACBC and CBC revealed similar outcomes for different sour cream product types when price was excluded; however, the CBC results differentiated products to a greater extent than ACBC with the same sample size considered.Practical ApplicationsConjoint analysis is a research technique widely utilized across multiple industries as a way of determining the utility of a product or a product feature. Adaptive choice‐based conjoint (ACBC) is a new form of conjoint analysis. Because of the format of ACBC studies, respondents may be more engaged in the survey‐taking experience and provide answers that are more in‐line with their actual choice behavior. Because of this, ACBC studies may reveal more accurate responses for specific attributes such as brand and/or price. ACBC studies may also require fewer respondents, which is advantageous when the audience is highly selective, or if money and/or time is a concern.