Performance of the hybrid hedonic scale as compared to the traditional hedonic, self-adjusting and ranking scales

In consumer tests, the nine-point hedonic scale has been widely employed for data collection. However, several researchers believe that this scale presents limitations, which decrease its discriminative power. It is thus important to identify alternative scales, presenting better performance than the traditional hedonic scale. This study compared the performance of the “hybrid hedonic scale”, the nine-point hedonic scale, the self-adjusting scale and the ranking scale with respect to: (i) the variability of sensory responses, (ii) discriminating power, (iii) adequacy of the data with ANOVA assumptions and, (iv) ease of use. Eighty consumers evaluated five samples of orange juice using the four above-mentioned scales. Both the scale's and the sample's presentation order were balanced among the consumers. Data normality was checked by the Shapiro-Wilks test and homoscedasticity by the Brown-Forsythe test. The discriminating power of the scales was analyzed by psample, the REGWF test and Power Analysis. The ranking test results were evaluated by Friedman's test and the ease of use by the Cochran-Mantel-Haenszel test. The results evidenced the superiority of the hybrid hedonic scale as compared to the structured and self-adjusting scales both with respect to the discriminating power and the ANOVA assumptions. The structured and hybrid hedonic scales were considered to be significantly easier to use than the self-adjusting scale.