Sample Size in Consumer Test and Descriptive Analysis

Abstract

This article deals with sample size (n) estimation by computer simulation using the variance of consumer and in-house sensory tests. The current sample size used in descriptive analysis was also examined. The sample size ranging from 20 to 200 was used to detect a difference ranging from 0.0 to 1.0 on a 9-point hedonic scale. For the simulated consumer data, significant difference was first observed at a difference of 0.60 when n = 40. Increasing the difference to above 0.60, the first significance likewise appeared when n = 40. Based on the variability used in the study, these results support the commonly cited sample size of 40-100. Thus, the role of the difference to be detected is very important in determining the sample size (base size). The variance can be obtained from historical data. In this study, the difference ranging from 0.60 to 1.00 is critical and can be used by the research and sensory analysts as a guide. Therefore, the analysts must have an idea of the size of hedonic differences among formula or products to be compared in determining the appropriate sample size. The power of the test for various sample sizes is provided through plots of power versus n. For descriptive analysis, the results showed that the recommended minimum is n = 5, noting that in most cases, judges differed by 1 unit on a 15-point rating scale. The power of the test is also reported for n ranging from 5 to 14 judges.

Physicochemical characteristics and sensory optimisation of pineapple leather snack as affected by glucose syrup and pectin concentrations

“…According to Moskowitz (1997), 40–50 panelists would be sufficient for sensory acceptability test. According to Gacula & Rutenbeck (2006), a sample size of 40–100 would be sufficient to detect a difference ( d ′) of above 0.6 based on the Thurstonian d ′ value for perceptible difference for overall liking measured on a 9‐point hedonic scale. According to Moskowitz (1994), forty‐five responses per formulation would provide dependable, reliable results that could be used to generate models relating sensory qualities and acceptability.…”

Invited Review: Sensory Analysis of Dairy Foods

“…Their results confirmed that minimal training was required for some texture and flavor attributes, whereas extensive training was required to discriminate other attributes. If the specific nature of the product differences and number of panelists are known, specific panel target performance (standard deviation) can be computed and modeled (Gacula and Rutenbeck, 2006). Generally, this information is not known and the panel leader must rely on data analysis collected from preliminary training sessions to confirm panel performance.…”

Does Information about Sugar Source Influence Consumer Liking of Products Made with Beet and Cane Sugars?

“…To truly understand the impact of information conditions regarding sugar source on product liking for a subgroup who favors one type of sugar source over the other, a larger number of panelist is needed. Between 40 and 100 panelists is necessary for a consumer test to obtain an adequate power (Gacula and Rutenbeck ).…”