Premium
A T hurstonian Analysis of the T wo‐ O ut‐of‐ F ive Test
Author(s) -
Ennis John M.
Publication year - 2013
Publication title -
journal of sensory studies
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.61
H-Index - 53
eISSN - 1745-459X
pISSN - 0887-8250
DOI - 10.1111/joss.12044
Subject(s) - test (biology) , mathematics , computer science , combinatorics , statistics , biology , paleontology
The T wo‐ O ut‐of‐ F ive test is a method of unspecified difference testing. Although its low guessing probability (1/10) gives promise that it might have high power, the theoretical underpinnings of the method have not yet been investigated. In this article, we offer the first such investigation, via T hurstonian analysis. This investigation reveals that the standard form of the T wo‐ O ut‐of‐ F ive test is more statistically powerful than the T riangle test, but not as powerful as the T etrad test. We then propose a new way of scoring T wo‐ O ut‐of‐ F ive data that yields a test with higher power and lower sample size requirements than the T etrad test, under the assumption that there is no additional noise from the evaluation of an additional stimulus. This last result is achieved without any experimental modification of the T wo‐ O ut‐of‐ F ive protocol. Tables for estimating the T hurstonian measure of sensory effect size, δ , for calculating the error in such estimates, and for recommended sample sizes are given. Finally, caution is given against incorrect instructions in the T wo‐ O ut‐of‐ F ive test – if respondents are asked simply to identify the two most similar samples, the resulting test has almost no power. Practical Applications This article shows that the standard form of the T wo‐ O ut‐of‐ F ive test is more powerful than the T riangle test, but is not as powerful as the T etrad test. The article then proposes a new method of scoring T wo‐ O ut‐of‐ F ive data that requires smaller sample sizes than the T etrad test, under the assumption that the evaluation of an additional stimulus does not lead to an increase in perceptual noise. When this alternate method of scoring the data is used, the test is called the T wo‐ O ut‐of‐ F ive test with forgiveness. Tables for estimating δ , the T hurstonian measure of sensory difference, together with B values that allow practitioners to calculate the variance in their estimates are given for both forms of the T wo‐ O ut‐of‐ F ive test. Tables of recommended sample sizes are also given in each case. Finally, it is noted that care must be taken to give correct instructions to respondents – it is possible to create a test with very low power if respondents are simply asked to identify the two most similar stimuli.