Tests of homogeneity of the odds ratio

Figure 1. Tests of homogeneity of the odds ratio for Newspaper subscription by Response, controlling for Income category
Tests of homogeneity of the odds ratio for Newspaper subscription by Response, controlling for Income category

The Breslow-Day and Tarone's statistics test the homogeneity of the odds ratio across categories of the layer variable. The null hypothesis for these tests assumes that the odds ratio for Newspaper subscription by Response is equivalent for each value of Income category. The significance values are greater than 0.10, indicating that the odds ratio is in fact homogenous, which means that you should not use Income category to further target the mailings.

Next