TRAVELING COURSE 2001
"Permutation Tests : A Guide for Practitioners"
May 1, 2001
A Presentation by Phillip Good



On May 1, 2001 the Detroit Chapter of the American Statistical Association, along with Wayne State University, participated in the American Statistical Association's traveling course program by offering a half day workshop titled Permutation Tests: A Guide for Practitioners. Forty-two statisticians attended the workshop. The speaker was Dr. Phillip Good of Information Research, a California based firm that provides product testing services and statistical consulting services. Dr. Good has over 30 years experience in aerospace, computer, medical devices, pharmaceutical and petroleum industries and is the author of two popular textbooks on resampling methods. He has also contributed numerous articles to leading probability and statistical journals. Students were given the historical background on resampling methods and a formal introduction to these methods. The course material applied to a wide variety of applications and students developed hypothesis tests and confidence intervals for one-, two, and k-sample comparisons, correlation and matched pairs. Examples included contingency tables, dose response, market response modeling, and courtroom use of confidence intervals. Recent advances in the field of model validation were discussed and participants learned when to apply the bootstrap, permutation and parametric methods.   Limitations of these approaches were also covered. The course was intended for statistical practitioners in medicine, business, engineering, the social sciences and professors of statistics as well as those who do statistical research and may not be familiar with resampling methods. Students also learned how to construct univariate and multivariate permutation tests for two- and k-sample comparisons, correlation, matched pairs, contingency tables and simple experimental designs. 


Back Row: Les Koska, Robert Kushler, Lance Heilbrun
Front Row: Cecilia Yee, Dave Fluharty, Phillip Good