Statistical Analysis and Data Display

Abstract

Students seeking master’s degrees in applied statistics in the late 1960s and 1970s typically took a year-long sequence in statistical methods. Popular choices of the course textbook in that period prior to the availability of high-speed computing and graphics capability were those authored by Snedecor and Cochran (1980) and Steel and Torrie (1960). By 1980, the topical coverage in these classics failed to include a great many new and important elementary techniques in the data analyst’s toolkit. In order to teach the statistical methods sequence with adequate coverage of topics, it became necessary to draw material from each of four or five text sources. Obviously, such a situation makes life difficult for both students and instructors. In addition, statistics students need to become proficient with at least one high-quality statistical software package. This book Statistical Analysis and Data Display can serve as a standalone text for a contemporary year-long course in statistical methods at a level appropriate for statistics majors at the master’s level and for other quantitatively oriented disciplines at the doctoral level. The topics include concepts and techniques developed many years ago and also a variety of newer tools. This text requires some previous studies of mathematics and statistics. We suggest some basic understanding of calculus including maximization or minimization of functions of one or two variables, and the ability to undertake definite integrations of elementary functions. We recommend acquired knowledge from an earlier statistics course, including a basic understanding of statistical measures, probability distributions, interval estimation, hypothesis testing, and simple linear regression.