Home-Grown Software a Trans-Atlantic Hit

A History of Stat-Ease, Inc.

Bringing design of experiments (DOE) to England might be likened to delivering coals to Newcastle, but that's what three U of M IT alumni1 accomplished via their company, Stat-Ease, Inc., when they displayed their Design-Expert® software,2 at the international Industrial Statistics in Action Conference at Newcastle University. Attendees from the United Kingdom, Europe and worldwide responded very enthusiastically. As testimonial, statisticians from SmithKline Beecham Pharmaceuticals put up a poster saying that easy-to-use software, specifically Design-Expert, must be made available to all experimenters to foster use of DOE.3

The irony of this trans-Atlantic software success is that DOE methods came to the USA from England. Sir Ronald Fisher, a distinguished British statistician, developed the basic tools while at Rothamsted Agricultural Station in the 1920's. He published the seminal "Design of Experiments" in 1935. During this period, most of the DOE work occurred (literally) in the field of agriculture. For example, in a pioneering study, researchers from the University of Minnesota made use of the statistical tools developed by Fisher to evaluate different types of barley.4 They randomly applied the various treatments within several blocks of land at various agricultural stations around the state. After removing the block differences and accounting for natural variability in yields, they saw statistically significant advantages to growing certain types of barley. The design used for this one-variable experiment is called a randomized block.

During World War II, a more sophisticated form of DOE, called factorial design, became a big weapon for speeding up industrial development for the Allied forces. These designs can be quite compact, involving as few as two levels of each factor and only a fraction of all the combinations, and yet they are quite powerful for screening purposes. After the war, a statistician at Imperial Chemical, George Box, described how to generate response surfaces for process optimization.5 From this point forward, DOE took hold in the chemical process industry, where factors such as time, temperature, pressure, concentration, flow rate and agitation are easily manipulated. Later, Box co-authored a textbook6 that formed the basis for the first DOE program by Stat-Ease--Design-Ease® software.

The principals of Stat-Ease learned DOE while working together at General Mills in its chemical research laboratory only a few miles north of the University campus. They recognized an opportunity when IBM came out with its original PC: The methods described by Fisher and Box could be incorporated in a menu-driven computer program that would make DOE easy for non-statisticians. By then, the chemical division of General Mills had been sold to Henkel of Germany. For various reasons, such as Minnesota being the "Siberia of the US," the new owners decided to disband all operations in the area.

At this juncture Pat Whitcomb decided to devote full time to Stat-Ease, a DOE software venture Pat started on a moonlighting basis in 1982. Pat incorporated Stat-Ease in April of 1985, and with programming help from his colleague Tryg Helseth, completed development of Design-Ease. In June of 1985 they sold their first copy, but sales didn't take off until 1987, when a professor from the University of Minnesota7 described Design-Ease as "incredibly easy to use" in a widely-read review of DOE software. With profits now rolling in, Stat-Ease could afford to bring Tryg on as a full-time programmer and hire another former colleague, Mark Anderson, as the business manager.

Young Pat   Young Mark   Young Tryg
Pat Whitcomb   Mark Anderson   Tryg Helseth

In 1988, the company released its first version of Design-Expert, which provided the tools for response surface methods (RSM) for process optimization. This package complemented Design-Ease. Design-Expert also provided innovative statistical tools for optimizing mixtures—a big attraction for users in the chemical process industries. With this product line extension, sales grew at a healthy rate and Stat-Ease added many new employees to handle orders, provide statistical help and program new features.

A major milestone occurred in 1996: Stat-Ease incorporated all of the features of Design-Ease into Design-Expert version 5 and translated it all to the graphical user interface of Windows. By then its user base approached six figures, so the demand for upgrades stimulated sales and allowed further hiring of programmers and other personnel. They contributed to development of version 6.0 of Design-Expert software released in 2000, and rounded out the array of designs, including the ability to combine mixture components with process factors. Design-Expert (now on version 8) is widely recognized as one of most powerful programs for doing DOE, yet is easy enough for use by non-statisticians who do industrial experimentation. Design-Expert is also used as a teaching tool by colleges and universities. It even comes packaged with one of the leading textbooks for DOE.8

The Stat-Ease mission is "Statistics Made Easy." This would be mission impossible without proper education. Unfortunately, most scientists and engineers get very little statistical training in college. Stat-Ease fills the gap with a variety of computer-intensive short courses from "Experiment Design Made Easy," the most popular workshop, up to advanced sessions on optimization and beyond. Aided by a stable of in-house and contract consultants, Pat and Mark teach hundreds of technical professionals the tools of DOE at dozens of workshops worldwide. For those who need help getting off the ground, they have authored two non-academic books that make DOE and response surface methodology (RSM) as easy as possible for non-statisticians.9

At the other end of the spectrum, the statisticians at Stat-Ease have been active in developing new tools for design of experiments. Professor Kinley Larntz from the School of Statistics at the U of M advised Stat-Ease from the beginning through 1999. He and Pat won the Shewell Award for best presentation at the prestigious Fall Technical Conference (FTC) in 1998.10 (This is an important forum for DOE that's co-sponsored by the Chemical and Process Industries Division and the Statistics Division of the American Society for Quality (ASQ) and the Section on Physical and Engineering Sciences from the American Statistical Association (ASA).) Professor Gary Oehlert, also from the U of M and an author on the subject of DOE,11 now provides statistical advice to Stat-Ease. He gave a well-attended presentation12 at the 2000 FTC held in Minneapolis (all roads lead to Minnesota!). In 2007 Pat and Gary won the Shewell Award for best presentation at the 2006 Fall Technical Conference. In 2011 Pat and Stat-Ease statistical consultant Wayne Adams won the Shewell Award for best presentation at the 2010 Fall Technical Conference—the 3rd time for Pat!

Stat-Ease now employs about more than a dozen employees at its headquarters in Minneapolis. The company is represented by consultant/resellers at major cities throughout the US and in most of the developed nations. The future looks very bright for Stat-Ease here in the center of North America, throughout the continent, and across the Atlantic to England and Europe. The next region to be conquered will be on the far side of the Pacific. Stat-Ease already has a foothold there via its connections to US-based multinationals, one of whom commissioned Pat to teach at its technical facilities in Japan, Taiwan and Korea. India has become a new major area of activity for DOE in the pharmaceutical field. It's now just a matter of time for the word to spread throughout the rest of the Far East on how easy DOE can be with Stat-Ease software.

References and Footnotes:

  1. Patrick Whitcomb (BSChE '73, MSChE '76), Mark Anderson (BSChE '75, MBA '80), Trygve Helseth (BSPharm '69, BSCSci '84).
  2. Design-Expert® software, Version 6.0, 2000.
  3. Marion Chatfield and Gillian Smith, SmithKline Beecham Pharmaceuticals, "Experiences of Promoting the Use of Design of Experiments in Synthetic Chemistry."
  4. See "X-Factor Files Divulge Minnesota Mystery:Alien Plot?" in the September 1999 issue of Stat-Ease's Stat-Teaser newsletter, which can be downloaded from here.
  5. Box and Wilson, "On the Experimental Attainment of Optimum Conditions," Journal of the Royal Statistical Society Ser. B, 13,1, 1951.
  6. Box, Hunter and Hunter, Statistics for Experimenters, John Wiley, 1978.
  7. Nachtsheim, "Tools for Computer-Aided Experiments," Journal of Quality Technology, Vol. 19, No. 3, July 1987, pp. 132-160.
  8. Montgomery, Design and Analysis of Experiments, 8th Ed., John Wiley, 2012. 
  9. Anderson and Whitcomb, DOE Simplified, Practical Tools for Effective Experimentation, 2nd Ed., Taylor & Francis/CRC Press/Productivity Press, New York, NY, 2007. 
  10. Larntz and Whitcomb, "Use of Replication in Almost Unreplicated Factorials," 42nd Annual Fall Technical Conference, Corning, NY, 1998.
  11. Oehlert, A First Course in Design and Analysis of Experiments, Freeman, 2000.
  12. Oehlert and Whitcomb, "A Unified Approach to Power Calculations for Designed Experiments," 44th Annual Fall Technical Conference, Minneapolis, 2000.

Appendix: Milestones for Stat-Ease, Inc.

  • 1969 Tryg graduates from University of Minnesota (U of M) school of pharmacy.
  • 1972 Tryg joins process development group at General Mills Chemical Incorporated (GMCI).
  • 1973 Pat graduates from U of M chemical engineering school and begins work at GMCI.
  • 1974 Mark hired as summer engineer at GMCI prior to senior year at U of M chemical engineering school.
  • 1976 Pat earns masters degree in chemical engineering from U of M.
  • 1977 GMCI bought by Henkel of Germany.
  • 1978 GMCI hires Professor Kinley Larntz from U of M's School of Applied Statistics to teach DOE to its R&D staff.
  • 1980 Henkel USA forms quality assurance group with Pat, Mark and Tryg as nucleus, Mark earns MBA from U of M.
  • 1982 Stat-Ease started by Pat Whitcomb to develop software for design of experiments (DOE).
  • 1982 Pat named Minnesota's Outstanding Young Chemical Engineer.
  • 1984 Tryg earns computer science degree from U of M, begins programming for Stat-Ease.
  • 1985 Stat-Ease is incorporated, and first software released in July. This is Design-Ease 1.04 for DOS written in Turbo Pascal.
  • 1986 Henkel moves R&D and other people out of Minnesota. Design-Ease 1.10 is released in November.
  • 1987 Glowing review of Design-Ease ("DE") published in Journal of Quality Technology and version 1.20 of Design-Ease is released in October.
  • 1988 version 1.01 of Design-Expert ("DX") written in BASIC code debuts in March. Tryg and Mark join Stat-Ease full-time.
  • 1989 2nd version of DX (version 2.00) released in October. This version is written in more efficient code (Pascal) and with greater capability. First full-time employee hired to do customer service.
  • 1990 First full-time programmer hired (in addition to Tryg)
  • 1991 DE 2.00 released in June with more versatile regression-based algorithm for analysis, and the second full-time programmer is hired.
  • 1992 DX3 released in October with 3D graphics and numerical optimization.
  • 1994 Million dollar award given to Stat-Ease, Inc. by Minnesota High Tech Association for surpassing this sales milestone with Design-Ease, DE3 released in June with graphical user interface (GUI) for Windows and Mac developed in C++. DX4 for DOS is released in April with stepwise regression and multicomponent constraints for mixtures.
  • 1995 Million dollar award given to Stat-Ease for Design-Expert.
  • 1996 www.statease.com goes up on Internet.
  • 1996 Forbes recommends Stat-Ease software for multivariable testing ("MVT").
  • 1997 V5 of DX combines DE4 and DX4 and converts to Windows, DE5 becomes a subset of DX. DX5 is released in January while DE5 debuts in April.
  • 1997 DX made optional with Doug Montgomery's 4th edition of "Design and Analysis of Experiments" by John Wiley and Sons publishers.
  • 1998 Larntz and Whitcomb, "Use of Replication in Almost Unreplicated Factorials," wins Shewell award at 42nd Annual Fall Technical Conference, Corning, NY.
  • 1999 Prof. Gary Oehlert succeeds retiring Prof. Larntz as statistical advisor.
  • 2000 Version 6 of DX released in April, Version 6 of DE released in October.
  • 2000 Mark and Pat co-author "DOE Simplified."
  • 2003 Stat-Ease web-based training site launched, www.statease.net
  • 2004 Mark and Pat co-author "RSM Simplified."
  • 2005 Version 7 of DX released September.
  • 2006 Version 7 of DE released in March.
  • 2007 Version 7.1 of DX released February.
  • 2007 Version 7.1 of DE released June.
  • 2007 Mark and Pat co-author "DOE Simplified, 2nd Edition."
  • 2007 Pat and Gary win the Shewell Award for best presentation at the 2006 Fall Technical Conference (FTC)—the 2nd time for Pat to win this award. (see page 8 on link)
  • 2009 Version 8 of DX released in December.
  • 2010 Version 8 of DE released in September.
  • 2011 Pat Whitcomb and Wayne Adams win the Shewell Award for best presentation at the 2010 Fall Technical Conference (FTC)—the 3rd time for Pat to win this award!
  • 2013 Pat Whitcomb receives the Charles W. Britzius Distinquished Engineer Award from the Minnesota Society of Professional Engineers and the Minnesota Federation of Engineering, Science and Technology Societies.
  • 2013 Version 9 of DX and DE released in December.
  • 2016 Version 10 of DX and DE released in January.