One-Way Analysis of Variance

12

643

Introduction

Many of the most effective statistical studies are comparative. For example, we may wish to compare customer satisfaction of men and women who use an online fantasy football site or compare the responses to various treatments in a clinical trial. With a quantitative response, we display these comparisons with back-to-back stemplots or side-by-side boxplots, and we measure them with five-number summaries or with means and standard deviations.

When only two groups are compared, Chapter 7 provides the tools we need to answer the question, “Is the difference between groups statistically significant?’’ Two-sample t procedures compare the means of two Normal populations, and we saw that these procedures are sufficiently robust to be widely useful.

In this chapter, we will compare any number of means by techniques that generalize the two-sample t test and share its robustness and usefulness. These methods will allow us to address comparisons such as