Preference segments: A deeper understanding of consumer acceptance or a serving order effect?

Cluster analysis is used widely to group consumers into homogenous “preference segments” from their patterns of overall liking ratings. In several case studies, cross tabulation of sample frequencies by serving orders reveals the assignment of consumers to segments may be due to the effect of serving order as opposed to genuine differences in acceptance patterns. This effect is defined as the “serving-order-by-segment effect”. To nullify this effect, four adjustment factors were developed and applied to the assessors’ data from six consumer tests. The adjustments differed in two ways: serving position and samples. Regarding serving position, two of the adjustments affected the first-serve responses only, while the other two adjustments affected the responses for all serving positions. Regarding samples, two of the adjustments used the same value to adjust the responses for all of the samples, while the other two adjustments used sample-specific values to adjust the responses for each sample. The number of samples in each of the six consumer tests varied from three to eleven. With the exception of the eleven sample study, cluster analysis on adjusted data yielded different conclusions than for non-adjusted data and results among the four adjustments varied. Serving-order-by-sample interaction plots may be useful in determining the most appropriate adjustment factor.