On repeated difference testing

Abstract

If the number of assessors in a difference test is not large enough to ensure the desired power of the testing procedure, then it is often advised to use assessors repeatedly. That is, each assessor performs the testing not just once but several times. There is a discussion going on, how results of a repeated difference testing are to be analysed. The present paper (as was to be expected) supports the point of view expressed in Kunert and Meyners (1999). It also tries to generalise their approach such that we get confidence limits. While the exposition concentrates on the triangle test, the approach is also applicable for other difference testing procedures (e.g. pairwise difference test, duo-trio test).