Statistics / Edition 9

STATISTICS IN THE NEW MILLENIUM

This ninth edition of Statistics is an introductory text emphasizing inference, with extensive coverage of data collection and analysis as needed to evaluate the reported results of statistical studies and make good decisions. As in earlier editions, the text stresses the development of statistical thinking and the assessment of credibility and value of the inferences made from data, by both those who consume and those who produce them. It assumes a mathematical background of basic algebra.

A briefer version of the book, A First Course in Statistics, is available for single semester courses that include minimal coverage of regression analysis, analysis of variance, and categorical data analysis.

NEW IN THE NINTH EDITION

• Exercise sets have been revised to provide a greater variety in level of difficulty. In addition to "Learning the Mechanics" exercises, "Applied Exercises" are categorized into "Basic," "Intermediate," and "Advanced" at the end of each section.
• All printouts from statistical software (SAS, SPSS, MINITAB, and STATISTIX) have been revised to reflect the latest versions of the software.
• Chapter 12 (Multiple Regression and Model Building) now includes a more detailed discussion of multicollinearity, with a real-data example and guidelines on detecting and dealing with the problem (Section 12.14).
• The sections in Chapter 13 (Categorical Data Analysis) have been reorganized, with emphasis on whether one or two qualitative variables are analyzed.
• An introductory section on distribution-free tests (Section 14.1) is now included in Chapter 14 (NonparametricStatistics).

TRADITIONAL STRENGTHS

We have maintained the pedagogical features of Statistics that we believe make it unique among introductory statistics texts. These features, which assist the student in achieving an overview of statistics and an understanding of its relevance in the social and life sciences, business, and everyday life, are as follows:

• Use of Examples as a Teaching Device—Almost all new ideas are introduced and illustrated by data-based applications and examples. We believe that students better understand definitions, generalizations, and abstractions after seeing an application.
• Exploring Data with Statistical Computer Software—Each statistical analysis method presented is demonstrated using output from four leading statistical software packages: SAS, SPSS, MINITAB, or STATISTIX. In addition, output and key stroke instructions for the TI-83 Graphing Calculator are covered in optional boxes.
• Statistics in Action—Each chapter concludes with a case study on a contemporary, controversial, or high-profile issue. Data from the study are presented for analysis and questions prompt the students to evaluate the findings and to think through the statistical issues involved. Additional cases appear on the Web site.
• Real Data Exercises—The text includes more than 1,200 exercises illustrated by applications in almost all areas of research. All the applied exercises employ the use of current real data extracted from a wide variety of publications (e.g., newspapers, magazines, journals, and the Internet). Many students have trouble learning the mechanics of statistical techniques when all problems are couched in terms of realistic applications. For this reason, all exercise sections ire divided into four parts:
• • Learning the Mechanics. Designed as straightforward applications of new concepts, these exercises allow students to test their ability to comprehend a mathematical concept or a definition.
  • Applying the Concepts—Basic. Based on applications taken from a wide variety of journals, newspapers, and other sources, these short exercises help students begin to develop the skills necessary to diagnose and analyze real-world problems.
  • Applying the Concepts—Intermediate. Based on more detailed real-world applications, these exercises require students to apply their knowledge of the technique presented in the section.
  • Applying the Concepts—Advanced. These more challenging real-data exercises require students to utilize their critical thinking skills.
• Quick Review—Each chapter ends with a list of key terms and formulas, with reference to the page number where they first appear.
• Language Lab—Following the Quick Review is a pronunciation guide to Greek letters and other special terms. Usage notes are also provided.
• Student Projects—Presented at the end of each chapter, these projects emphasize gathering data, analyzing data, and/or report writing.

FLEXIBILITY IN COVERAGE

The text is written to allow the instructor flexibility in the coverage of topics through "optional" sections in relevant chapters and occasional footnotes. Suggestions for covering two topics, probability and regression, follow.

• Probability and Counting Rules—One of the most troublesome aspects of an introductory statistics course is the study of probability. Probability poses a challenge for instructors because they must decide on the level of presentation, and students find it a difficult subject to comprehend. We believe that one cause for these problems is the mixture of probability and counting rules that occurs in most introductory texts. We have included the counting rules in a separate optional section at the end of Chapter 3 (Probability). In addition, all exercises that require the use of counting rules are marked with an asterisk (*). Thus, the instructor can control the level of coverage of probability.
• Multiple Regression and Model Building—This topic represents one of the most useful statistical tools for the solution of applied problems. Although an entire text could be devoted to regression modeling, we feel that we have presented coverage that is understandable, usable, and much more comprehensive than the presentations in other introductory statistics texts. We devote two full chapters to discussing the major types of inferences that can be derived from a regression analysis, showing how these results appear in the output from statistical software and, most important, how to select multiple regression models to be used in an analysis. Thus, the instructor has the choice of a one-chapter coverage of simple linear regression (Chapter 11), a two-chapter treatment of simple and multiple regression (excluding the optional sections in Chapter 12 on model building), or complete coverage of regression analysis, including model building and regression diagnostics. This extensive coverage of such useful statistical tools will provide added evidence to the student of the relevance of statistics to real-world problems.
• Footnotes—Although the text is designed for students with a non-calculus background, footnotes explain the role of calculus in various derivations. Footnotes are also used to inform the student about some of the theory underlying certain methods of analysis. These footnotes allow additional flexibility in the mathematical and theoretical level at which the material is presented.