Abstract

For two-way contingency tables with ordered categories, Tomizawa (1992) considered the parsimonious Linear-by-Linear association model. This model can be described in terms of fewer parameters than the Linear-by-Linear association model (Agresti, 1983). The purpose of this paper is (i) to define the parsimonious independence model, (ii) to show the parsimonious independence model holds if and only if the parsimonious Linear-by-Linear association model holds and the each one of various correlation coefficients is equal to zero, and (iii) show the statistic for testing the parsimonious independence model is asymptotically equivalent to the sum of test statistics for the decomposed models.

This work is licensed under a Creative Commons Attribution 4.0 License.