Treatment In a 2018 study by Zhu et al. reported in The Lancet, researchers conducted an experiment to determine the efficacy and safety of the drug dorzagliatin in the treatment of patients with Type 2 diabetes. In this double-blind study, patients were randomly assigned to one of two treatment groups (drug or placebo) and the glucose levels of the two groups were compared after 12 weeks. If we test whether treatment group is associated with glucose level, are we doing a test of homogeneity or a test of independence?