Adequate number of consumers in a liking test. Insights from resampling in seven studies
Résumé
The recommended number of consumers to be enrolled in a hedonic test comparing several products usually ranges from 50 to 100, at least if no liking segmentation is sought. This paper seeks to examine whether such a panel size range is adequate, by means of 7 trials with different levels of product space complexity. Five types of products were tested: Two varied in fattiness and sweetness and were tested under the same conditions in two separate laboratories (4 trials); the remaining three, varying in taste and texture, were each tested in a different laboratory (3 trials). Each of the 7 trials was run by a different laboratory. Each of the seven laboratories enrolled in its trial 150 consumers who gave liking scores on a set of 5 or 6 products. The method used to derive adequate panel size consists in removing k subjects from the 150 in the original panel and then measuring the loss of information in product comparisons. Four criteria to be maximized were used: The correlation between the two vectors of product mean scores, the RV coefficient between the two product spaces, the Fisher discrimination ratio among products and the concordance rate in product pair comparisons. For each k, k = 0, ..., 130 by 10, one thousand incomplete panels were simulated by resampling with replacement. Results showed that adequate panel size varied from 20 to 150. Since the level of heterogeneity in consumer preferences was rather similar across trials, panel size should depend on product sensory differences. The variation in panel size recommendation was thus mostly due to the level of complexity of the product space.