Abstract: | A statistical procedure for comparing the performance of a new product with the existing products on the basis of sensory characters has been developed. A test statistic was evolved for testing the null hypothesis of equality of treatment effects in the case of fractional triad comparisons. The null distribution of the test statistic has been obtained and it is found that it has a χ2-distribution for large number of observations. The procedure is quite simple and is based on a distribution-free test requiring only ordinal scale measurement. The method of analysis has been explained by a numerical example. |