CONSUMER DATA - STATISTICAL TESTS FOR DIFFERENCES IN DISPERSION

Three types of category or rank data, commonly obtained in consumer ta ste tests will be analysed via a ranks transformation followed by a pa rtition of Pearson's X(2). These three types of data are: independent samples data with ties, related samples data without ties, and related samples data with ties. The data are summarized as two-way tables of counts, where some of the counts are zero or small. Thus Monte Carlo P values are appropriate. The partition of X(2) method places a number of common nonparametric statistics in the same family. All the example s relate to actual taste tests done at the CSIRO Food Research Laborat ory.