Food and Drug Interaction: What Role Does Statistics Play?
Thomas E. Bradstreet · College Mathematics Journal · 2000
I provide the data from the experiment. This example can be used to motivate classroom discussions and home work assignments. The data set can be used to illustrate the idea of paired vs. independent data; one sample normal theory estimation and hypothesis testing procedures such as the paired Mest, and the corresponding point estimator and confidence interval, the Wilcoxon signed rank test and the corresponding Hodges-Lehmann point estimator and Tukey confidence interval; two sample distribution-free procedures such as the Wilcoxon rank sum test, and the corresponding Hodges-Lehmann estimator and Moses confidence interval; outliers; exploratory data analysis methodologies; graphical displays; and the normal theoiy ANOVA and corresponding confidence intervals for the two-treatment, two-period, two-treatment-sequence crossover design. At the end of the article, I provide access to twenty-two other pedagogically useful data sets. Consider the following scenario. A new antihypertensive therapy has been shown to be safe, well tolerated, and effective in lowering the diastolic blood pressure in patients with hypertension. Specifically, the parent compound, Drug P, is processed by the human body and its metabolite, Drug M, is the result. Both Drug P and Drug