Edited by Connie M. Borror
Statistical Process Adjustment for Quality Control.
by Enrique del Castillo
Teaching Statistics, Resources for Undergraduate Instructors
edited by Thomas L. Moore
A Second Course in Statistics: Regression Analysis, 6th ed.
by William Mendenhall and Terry Sincich
Mani Janakiram, Intel Corporation, Chandler, AZ 85226.
Statistical Process Adjustment for Quality Control by Enrique del Castillo. John Wiley & Sons, New York, NY, 2002. xviii + 357 pp. $94.50.
THE reduction of process/product variability is of great interest to both industrial practitioners and academics. In practice, the traditional statistical process control (SPC) techniques, such as the Shewhart, CUSUM, and EWMA charts, are being supplemented with multivariate charts and other techniques. Engineering control techniques using feedback/ feedforward adjustments have also led to significant progress, particularly with the availability of powerful computers. A new methodology called advanced process control (APC) has emerged in the semiconductor industry and focuses on the integration of these two types of techniques. Dr. del Castillo's book provides a very good treatment of these techniques and approaches that should be of interest to both academics and practitioners. However, a practicing process/control engineer may find the advanced statistical aspects provided in this book to be challenging for implementation purposes. For example, the SAS code provided in the book needs more details. The author provides a very useful list of references. Errata are given at the author's website (www.ie.psu.edu/faculty/castillo/Errata.pdf).
This book provides real and simulated examples for a better understanding of concepts and information on how to apply the process adjustment methods. Good coverage of software tools (Minitab, SAS, and Matlab) is also provided in this book.
The text consists of the following nine chapters:
In addition to covering the basic SPC techniques, ARIMA and transfer function model identi.cation and fitting are presented with examples in the first section. I am sure that many readers will also appreciate the primer provided on z-transforms.
Process adjustment techniques through minimum variance controllers, PI, PID, EWMA controllers, and double-EWMA controllers are given comprehensive treatment, with relevant examples. Selftuning controllers and adaptive controllers are also explained in the second section.
The last chapter provides an approach to process control through multivariate ARMA and ARMAX techniques. Given process complexity, the multivariate approaches to process control are very applicable in many industries.
Another book to read in this area of advanced process control is that of Box and Luceño (1997). Dr. del Castillo's book provides the much-needed fundamentals in the area of advanced process control. In this book SPC and control theory are explained well, and it can be used as a stand-alone or as a companion to Box and Luceño (1997) by both academics and practitioners.
Box, G. E. P. and Luceño, A. (1997). Statistical Control by Monitoring and Feedback AdjustmentK. John Wiley & Sons, Inc. New York, NY.
Lloyd S. Nelson, Statistical Consultant, Londonderry, NH 03053-3647.
Teaching Statistics, Resources for Undergraduate Instructors edited by Thomas L. Moore. The Mathematical Association of America and The American Statistical Association. ix + 222 pp. $31.95.
THE general problem addressed by this book is how best to teach statistics to beginning students. The authors make the case that the answer is simply data, data, data. That is to say, let the concepts come in through the doorway of data. The book is divided into six sections as follows.
Section 1. Hortatory Imperatives; Section 2. Teaching with Data; Section 3. Established Projects in Active Learning; Section 4. Textbooks; Section 5. Technology; and Section 6. Assessment.
In the first section, the authors make the case for "more data, less lecturing." This sets the tone for the entire book. I believe that anyone who has taught this subject can not have failed to observe that students' interest is highest when it is focused on data that they themselves have gathered. The purpose of this book is to emphasize this point and to illustrate how to take advantage of it.
There are numerous examples of student projects that are described in detail together with the analyses. This could very well turn out to be the most useful part of the book. My experience is that students very frequently have great difficulty in coming up with good projects, i.e., projects that will have a significant learning component. This book can be a tremendous help in this regard.
A good analogy for this type of teaching and learning can be found in a sport, say tennis. No matter how perfectly the actions of using the racquet are described (including which muscles do what), no description can take the place of a few practice sessions. For those who would like to enjoy optimum popularity with their statistics course, this is the text for them. Oral presentations of projects by the students will give them useful experience. Students will both enjoy the course and learn important working principles that they should and will take with them: and all this from such a modestly priced book!
The following brief editor's review is of new editions, collections of papers, or other books that may be of interest to some readers.
Connie M. Borror,, Industrial and Management Systems Engineering, Arizona State University, Tempe, AZ 85287-5906.
A Second Course in Statistics: Regression Analysis, 6th ed by William Mendenhall and Terry Sincich. Pearson Education Inc., Upper Saddle River, NJ. xv + 880 pp. $106.67.
THE sixth edition of this text has several new and updated features that make it very attractive for an introductory course in regression analysis. Some of the features include more comprehensive computer output from SAS, SPSS, and Minitab, and tutorials for each of the statistical packages, provided in three separate appendices. Many new examples and exercises have been added throughout the text and, in general, cover a wide range of applications.
There are the following twelve chapters, .ve complete case studies, and seven appendices:
The targeted audience includes undergraduate students (statistics or non-statistics majors) and graduate students in non-statistics majors. Mathematical details have been relegated to the appendices, allowing greater emphasis to be placed on interpretation of results in each chapter. This does not mean that statistical notation has been sacrificed in the text. On the contrary, the authors successfully present the techniques, the goal of each technique, and the interpretation of the results. The appendices are a good supplement for those students who need more detailed development of the formulas and methods. This book should be considered when choosing a text for a regression course that is aimed at non-statistics majors.
John Wiley & Sons, 605 Third Ave., New York, NY 10128; (800) 352-3566; http://www.wiley.com
Prentice-Hall, Inc., One Lake Street, Upper Saddle River, NJ 07458; (800) 282-0693; Fax (800) 835-5327; www.prenhall.com