Post-Fisherian Experimentation: From Physical to Virtual

Abstract

Fisher’s pioneering work in design of experiments has inspired further work with broader applications, especially in industrial experimentation. This article discusses three topics in physical experiments: principles of effect hierarchy, sparsity, and heredity for factorial designs, a new method called conditional main effect (CME) for de-aliasing aliased effects, and robust parameter design. I also review the recent emergence of virtual experiments on a computer. Some major challenges in computer experiments, which must go beyond Fisherian principles, are outlined.

• Aliased effects
• Computer experiments
• Conditional main effects
• Effect heredity
• Effect hierarchy
• Effect sparsity
• Kriging
• Robust parameter design
• Uncertainty quantification

Additional information

Notes on contributors

C. F. Jeff Wu

C. F. Jeff Wu is Professor and Coca Cola Chair in Engineering Statistics, School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332-0205 (E-mail: [email protected] ). Thanks go to the Fisher lectureship committee for the invitation to deliver the Fisher lecture at the 2011 Joint Statistical Meetings and my mentors Peter Bickel and George Box.