SUMMARY The problem of testing for non-additivity in a two-way classification has been considered in this paper where the mean μii can be expressed as μ+αi+βi where αi and βi are the effects of the two ways of classification (i = 1, …,p;j = 1, …,q). Tukey (1949) has suggested a test for non-additivity. The power function of this test has been found in this paper for alternatives of the form μii = μ+αi+βi+cαi βi and numerical calculations made for the case of p = q = 6. For the sake of comparison the special case of α2i–1 = α2i, β2j–1 = β2j has also been considered, when an F-test is available with d.f. (4, 27). It is seen that the power of Tukey's statistic is slightly less than that of the F-test for smaller values of C 2 σ2 and ∑αi2σ2=∑βj2σ2, but for a wide range of values of these parameters, the performance of Tukey's statistic is better.
No takes yet. Share an insight, caveat, or question.
Ghosh et al. (1963) studied this question.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: