ABSTRACT
Students of statistics soon learn that there is a dazzling array of mathematical techniques for analyzing data, testing hypotheses, and estimating the probability of error. Nevertheless, the controversies reviewed in this book suggest that students and practitioners alike need to look more closely at the limitations of the data to which the sophisticated techniques are applied. Repeatedly, the origin of policy disputes can be traced to questions about the underlying data: Why are only certain data collected? Why are the data organized into particular categories? Why are some data reported as fact to the exclusion of other equally reputable data? And why do the data so often generate apparently conflicting statistics? In order to answer these questions, it is convenient to divide the debates discussed in the previous chapters into categories based on the core source of controversy in the underlying data.
