Revisiting French tomato data: Cluster analysis with incomplete data.

• Multiple imputations (MI) is used to deal with missing data. • Two new approaches are taken, yielding similar results for the data at hand. • Simulations are used to try to understand how many MIs are needed. • Gaussian mixture modeling (GMM) is used for cluster analysis. • Polynomial regression models are used for understanding cluster drivers. The analysis of French tomato data from a 2004 Sensometrics workshop is revisited. The workshop posed two questions (1) are there consumer segments in hedonic data and (2) if there are segments, can they be characterized using consumer and tomato attributes. The challenge with the hedonic data is a large amount of missing data. "Probabilistic" solutions to the latter via multiple imputation are explored. In addition to more traditional methods, polynomial models are used to answer the second question. [ABSTRACT FROM AUTHOR]