Attacking Complex, Unstructured Problems with Statistical Engineering
Roger W. Hoerl
Applied Statistics Laboratory, GE Global Research, Niskayuna, NY, United States

Statistical problems presented at conferences or in journals typically correspond to a recognizable textbook chapter (Meng 2009). However, the problems that statisticians actually face are often too large, complex and unstructured to be solved with any single statistical method. Rather, statisticians must develop an overall strategy to attack the problem, one that requires integration of several individual techniques. Unfortunately, statisticians rarely receive formal training in how to do this integration into overall problem solving strategies, and there is a dearth of underlying theory and reference literature to guide statisticians attempting to attack such complex, unstructured problems. Hoerl and Snee (2010) have defined statistical engineering as “the study of how to best utilize statistical concepts, methods, and tools and integrate them with information technology and other relevant sciences to generate improved results.” This session will propose that statistical engineering can provide the needed framework from which to effectively attack large, complex, unstructured problems - those that do not correspond to a recognizable textbook chapter. Further, development of statistical engineering as a discipline can provide the sound theoretical basis and body of literature needed to guide statisticians in the integration of various methods into overall strategies needed to solve these types of problems.


Meng, X. (2009) “Desired and Feared – What Do We Do Now and Over the Next 50 Years?” The American Statistician, 63, 202-210.

Hoerl, R.W., and Snee, R.D. (2010), “Moving the Statistics Profession Forward to the Next Level,” The American Statistician, 2010, 64, 1, 10-14.

Keywords: Statistical Engineering; Unstructured Problems; Problem Solving; Integration

Biography: Dr. Roger W. Hoerl leads the Applied Statistics Laboratory at GE Global Research, which focuses on new product and service development within each of the GE businesses. Dr. Hoerl has been named a Fellow of the American Statistical Association and the American Society for Quality, and has been elected to the International Statistical Institute and the International Academy for Quality. He has received the Brumbaugh and Hunter Awards, as well as the Shewhart Medal, from the American Society for Quality, and the Founders Award from the American Statistical Association. In 2006 he received the Coolidge Fellowship from GE Global Research, honoring one scientist a year from GE Global Research for lifetime technical achievement.