This article was downloaded by: [University of Colorado - Health Science Library] On: 26 December 2014, At: 02:44 Publisher: Taylor & Francis Informa Ltd Registered in England and Wales Registered Number: 1072954 Registered office: Mortimer House, 37-41 Mortimer Street, London W1T 3JH, UK
The American Statistician Publication details, including instructions for authors and subscription information: http://www.tandfonline.com/loi/utas20
Even You Can Learn Statistics: A Guide for Everyone Who Has Ever Been Afraid of Statistics a
Yolande Tra a
Rochester Institute of Technology Published online: 01 Jan 2012.
To cite this article: Yolande Tra (2007) Even You Can Learn Statistics: A Guide for Everyone Who Has Ever Been Afraid of Statistics, The American Statistician, 61:2, 182-182, DOI: 10.1198/tas.2007.s77 To link to this article: http://dx.doi.org/10.1198/tas.2007.s77
PLEASE SCROLL DOWN FOR ARTICLE Taylor & Francis makes every effort to ensure the accuracy of all the information (the “Content”) contained in the publications on our platform. However, Taylor & Francis, our agents, and our licensors make no representations or warranties whatsoever as to the accuracy, completeness, or suitability for any purpose of the Content. Any opinions and views expressed in this publication are the opinions and views of the authors, and are not the views of or endorsed by Taylor & Francis. The accuracy of the Content should not be relied upon and should be independently verified with primary sources of information. Taylor and Francis shall not be liable for any losses, actions, claims, proceedings, demands, costs, expenses, damages, and other liabilities whatsoever or howsoever caused arising directly or indirectly in connection with, in relation to or arising out of the use of the Content. This article may be used for research, teaching, and private study purposes. Any substantial or systematic reproduction, redistribution, reselling, loan, sub-licensing, systematic supply, or distribution in any form to anyone is expressly forbidden. Terms & Conditions of access and use can be found at http:// www.tandfonline.com/page/terms-and-conditions
sample sizes. The naive reader will be lead to believe the t test is the answer for everything involving a measure of center. In summary, there are ideas that all citizens should understand that are very clearly presented in SASLD. The important concepts of statistics are emphasized throughout the book, and the authors have endeavored to adhere to the GAISE guidelines. The result is a very nice, statistically sound text that will appeal to those statisticians teaching the so-called “art appreciation” course. Alan T. Arnholt Appalachian State University REFERENCES
Downloaded by [University of Colorado - Health Science Library] at 02:44 26 December 2014
“Guidelines for Assessment and Instruction in Statistics Education (GAISE) for the College Introductory Course.” Available online at http:// www.amstat. org/ education/ gaise. Hollander, M., and Wolfe, D. A. (1999), Nonparametric Statistical Methods, New York: Wiley. Moore, D. S. (2004), The Basic Practice of Statistics, New York: W. H. Freeman.
Even You Can Learn Statistics: A Guide for Everyone Who Has Ever Been Afraid of Statistics. David M. Levine and David Stephan. Upper Saddle River, NJ: Prentice Hall, Inc., 2005, xix + 281 pp., $19.95(P), ISBN: 0-13-146757-3. This book is a comprehensive guide to the most commonly used descriptive and inferential statistical methods. Each concept is conveyed in a simple and understandable way. The typical fear of the course is taken away, and the stress is on learning and practicing the methods. This book is a useful resource for a formal statistics course or for information on a specific analysis. Effort was taken to make the book accessible to the layman. More specifically, a two-step concept-interpretation scheme is employed. First, an idea is defined in plain language, free of mathematical terms. Then, an interpretation follows to emphasize the idea’s importance and/or its misinterpretations. Examples follow the two-step presentation. I appreciated this presentation style and believe that it is an outstanding medium in which to communicate more advanced topics. The book gets to the point quickly and avoids wordy or lengthy explanations. Mathematical prerequisites are minimal. In this book, “every concept is explained in plain English, without the use of higher mathematics or mathematical symbols” (p. xvii). However, the text contains some “equation blackboards” (an icon named “Interested in Math”), an option for those interested in mathematical formulations. Comprehension is not sacrificed if this icon is skipped. One of the best features of the book is the “Worked-out Problems”, which offer complete solutions that reinforce key concepts. Problems can also be worked with the provided “calculator keys” or “solution spreadsheets”. Appendix A reviews the use of these two practicing tools. Problems are typically based on real data and are available from the Web site of the book. Throughout the book, there are “Important Point” icons, that stress essential explanations. The book is sensibly divided into two parts: introductory material and four reasons to learn statistics (describe information, draw conclusions, obtain reliable forecasts, and improve processes). Each part contains several chapters, and each chapter is broken down into sections. Most chapters contain an “End-ofChapter” feature and end with a “One-Minute Summary”, a quick highlight of the significant topics and, whenever appropriate, a guide for statistical applications. These features are followed by a “Test Yourself” quiz complete with answers and references for further investigation. The presentation and flow of ideas from chapter to chapter is clear and fluid. The first chapter presents the basic vocabulary of statistics. Four important components are prominent: branches of statistics (descriptive and inferential), data collection, sources of data, and sampling theories and methods. The second chapter covers data presentation in charts and tables. It closes with a section on misuse of graphs. Guidelines are given for producing good graphs. Part II, on important reasons to learn statistics, is the essence of the book. Here, one chapter is devoted to various visual descriptions of data, depending on the type of variable (numerical, categorical, ordinal, etc.). Another chapter provides descriptions and definitions of a numerical variable related to location, variation, and shape. The next chapter addresses the foundations of probability. This chapter is essential to master before tackling the later inferential chapters. Discrete and continuous probability models are developed. Classical examples using coins, cards, and dice evolve to interesting real-life examples such as investments, shopping on a Web site, and customer arrival times at a bank.
182 Reviews of Books and Teaching Materials
The second important reason to learn statistics is to draw conclusions about the population based on a single sample. This topic is elaborated upon in four consecutive chapters. The first of these covers two subjects: sampling distributions and confidence intervals. I particularly liked the simulation-driven presentation of sampling distributions. The reader is then introduced to sampling errors and confidence interval concepts. The last sections in this chapter present confidence intervals for means and proportions. Basic schemes and principles of hypothesis testing comprise the second chapter. The rationale of hypothesis testing is explained in a single section. Highlights include the two hypothesis-testing errors and their associated probabilities, p values, and practical significance versus statistical significance. This chapter explains the five customary steps in performing a hypothesis test. A last section on types of hypothesis tests connects this material to Chapter 3 (hypothesis testing for two groups). The focus here is on the difference between two means or proportions. Methods to check the assumptions are referenced, and alternative methods are discussed when certain assumptions are violated. The choice of an appropriate test for any two-group set of data is emphasized. The fourth chapter extends hypothesis testing to multiple groups. Chi-square tests for categorical variables and one-way analysis of variance (ANOVA) tests are presented. Nonparametric alternatives to the F test and procedures to assess the one-way ANOVA assumptions are discussed with supporting references. Simple linear regression is then presented, mainly as a method to obtain reasonable forecasts. Regression is motivated as a descriptive tool and as a method to investigate and predict mathematical associations between two variables. Important sections cover residual analysis and inferences about the regression slope parameter. The closing chapter expands on the fourth important reason for learning statistics: improving processes. It includes a highly readable account of the basics of total quality management coupled with six sigma management methodology. An imagined reality series on Deming’s red bead experiment is used to demonstrate the natural (common) variation in processes. To determine the causes of variation, control charts for categorical and numerical variables are presented. Four appendixes supply TI statistical calculator information, Microsoft Excel settings, statistical tables, and a review of background arithmetic and algebra. The book is appropriate for self-study for readers with different backgrounds in mathematics. In my opinion, it is a great resource for college students taking a basic statistics course. It would also likely help any instructor looking to teach basic statistical topics at a very elementary level. I enthusiastically recommend this book and have used it as a concept reference for my own teaching. Yolande Tra Rochester Institute of Technology
Essentials of Statistics for Business and Economics (4th ed.). David R. Anderson, Dennis J. Sweeney, and Thomas A. Williams. Stamford, CT: Thomson Learning, 2006, xxiiii + 643 pp., $134.95(H+CD+InfoTrac), ISBN: 0-324-22320-X. Essentials of Statistics for Business and Economics is an introductory statistics textbook for business students. It covers the usual material in 13 chapters. It is a well laid out book with many examples, and each chapter has a summary, glossary, and a display of key formulas. The authors achieve their aim of writing for a nonmathematical audience and teach the material by showing the application of the statistics. The methodology is outlined without bogging down in advanced statistical proofs. The section headings within each chapter are very clear and precise, and the diagrams are large and clear. Each chapter has “Case Problems” and “Self-Test” questions with answers in an Appendix. Computing issues are covered through Minitab and Excel appendixes at the end of most chapters. The CD-ROM contains the 160 datasets used in the book in both Excel and Minitab versions. The final endpage is a useful map of where the files in the data disk are used in the book. The recent trend in undergraduate statistics is to teach inference based on the σ known/σ unknown approach rather than a small/large sample size approach. So the standard normal distribution is used for interval estimation and hypothesis tests when σ is known, and the t distribution is used when σ is unknown. This is the modern approach, and it successfully conveys inference methods to large classes of students (200+). (Of course, the instructor must stress when normality of the population is being assumed.) The fourth edition also makes greater use of p values in hypothesis testing since these are the standard output of statistical software packages.
