Planning and Executing Credible Experiments

Detailed Contents ix

About the Authors xxi

Preface xxiii

Acknowledgments xxvii

About the Companion Website xxix

1 Choosing Credibility 1

2 The Nature of Experimental Work 7

3 An Overview of Experiment Planning 27

4 Identifying the Motivating Question 31

5 Choosing the Approach 39

6 Mapping for Safety, Operation, and Results 51

7 Refreshing Statistics 65

8 Exploring Statistical Design of Experiments 87

9 Selecting the Data Points 107

10 Analyzing Measurement Uncertainty 143

11 Using Uncertainty Analysis in Planning and Execution 197

12 Debugging an Experiment, Shakedown, and Validation 231

13 Trimming Uncertainty 243

14 Documenting the Experiment: Report Writing 269

Appendices

A Distributing Variation and Pooled Variance 283

B Illustrative Tables for Statistical Design 289

C Hand Analysis of a Two-Level Factorial Design 293

D Free Recommended Software 307

Index 311

Planning and Executing Credible Experiments is a comprehensive presentation of what needs to be done in the development, execution, and interpretation of experiments. It includes a detailed discussion of uncertainty quantification that often is overlooked in presentation of experimental data. It is an essential reference for anyone who uses experiments for answering key questions and making data-based decisions in engineering, science, medicine and business.--Professor C.T. Bowman, Mechanical Engineering Department, Stanford University

Planning and Executing Credible Experiments is a must read for any engineer who either is a test engineer or supervises a test engineer. I believe nothing of substance relative to experiments has been left out of this text. I'm giving a copy to my nephew who is an undergrad engineer, I can't think of a better gift...it keeps on giving. It's a great reference.--James Callas, Test Chief at Caterpillar, P.E. (semi-retired)


Finally available, the long-awaited book Planning and Executing Credible Experiments written by Moffat & Henk! I have eagerly anticipated this book being published. While this statement may seem enthusiastic, I assure you that we who had the privilege of attending Professor Moffat's classes at Stanford University will understand this feeling of mine. His graduate courses in experimental methods in thermosciences were worth our intense effort. He packed his classes with weighty content: each thought, each reflection. After each class, the same litany among us students ... "were you able to record everything? ... Can we share our notes?" We dreamed of having this book to accompany the lessons of the great master!

In my opinion, "Planning and Executing Credible Experiments" is the bible of the experimentalist. A complete book. By conceptualizing the credibility of the experiment and the systemic view of experimental work, it lifts the responsibility of the experimentalist, enabling him, in a critical way, to validate his experiments. The book discusses strategies and tactics of the experimental work, differentiating it from theoretical analysis. With the authority of one of the respected founders advancing the analysis of measurement uncertainty, this book is dense with concepts, practical examples, and statistical tools. This book demonstrates with clarity and propriety "what does uncertainty analysis tell the experimentalist?"

Having this book in hand empowers experimentalists in every department at my university.

To every university in other countries: I highly recommend this book to improve the impact and credibility of their research, science, and engineering schools. Just as it benefits Stanford-trained researchers.

Any manufacturer, business and industry aiming to improve its operations will find the strategies in this book invaluable because its tools boost the Deming cycle.

In Sum: Planning and Executing Credible Experiments guides experimentalists to perform experiments with results they can justify and defend.--Prof. M. N. Frota, Pontifical University of Rio de Janeiro / BRAZIL

ROBERT J. MOFFAT, PHD, is a Professor Emeritus of Mechanical Engineering at Stanford University. He proved engines for General Motors and is the former President of Moffat Thermosciences, Inc. His main areas of research include convective heat transfer in engineering systems, experimental methods in heat transfer and fluid mechanics, and biomedical thermal issues.

ROY W. HENK, PHD, designed aerospace engine components and has conducted experimental tests in industry, a government lab and internationally. He has been a Professor in the USA, South Korea, and most notably at Kyoto University in Japan. His research includes experiment design, energy conversion, turbomachinery, and thermal fluid physics.