Journal of Sensory Studies vol. 18, no. 6, pp. 487 - 516
SCI; SCIE; SCOPUS
Paired preference tests given to over 2000 consumers with putatively identical stimuli are discussed. Response conditions and consumer groups were varied and the proportions of preference and no preference responses were noted. Logical objections are present to extract preference data from hedonic scales. The use of these response frequencies as expected frequencies in chi squared analysis is illustrated, after adjustments for counterbalancing.