Jul 7, 2020 11:35 AM
| Last Modified: Jul 9, 2020 11:59 AM
The notion of doingdesign of experiments (DOE) initially can beliketasting cilantro for the first time:polarizing, sincemost people either love it or hate it.Such was a conversation I had with Tim Gardner,scientist,CEO and founder ofRiffyn, as we prepared for a recentStatistically Speaking episode on the power of structured experimentation in science and engineering.
PeterGoos, professor, authorand researcher, gave an excellent plenary on fast-tracking innovation using DOE to set the stage for the panel discussion.He highlighted the need for innovation, described what successful innovation requires,and shared some compelling success stories. Though he talked about successes in innovation, he made it clear thatwithoutusing a structured approach to systematically explore multiple factors and the effects they can have on the phenomenon under study, you are ultimately limiting yourself to haphazard trial and error or doing one-factor-at-a-time experiments, which are sub-optimal in so many ways.
The panelists' conversationthat followedwas fascinating.VickySvidenko,wholeads the Quantum Systems Integration team atMicrosoft;Michael Anderson,seniorengineer in the new productandprocess development division of Corning’s Science & Technology organization; BradleyJones, Distinguished Research Fellow at JMP;and Tim each brought valuable and varied perspectives to bear.
Tim described his (and some others’) reactiontousingDOEfor the first time:“It blew me away; the power of DOE…it’s extraordinary what I can get done … it changed my life.”
Michael agreed, explaining that with a well-designed experiment “you can see the entire world of your process,”rather thanjust one area where things may work somewhat but not optimally.
We explored theirorganizations’ culturesof experimentationas well. Vicky describesadopting DOEas a journey, but one that has had a snowball effect. She explained that Microsoft’s culture encouragespeople to look for opportunities to experiment and celebratesthe acquired learning.
Not all scientists, engineers or data explorers who want rapid innovationconduct designed experiments, often because of their initial reaction. (Many practitioners, like Brad, consider DOE a misnomer and wouldprefer the term“active learning.”) But the benefits they forgo, plus the waste and opportunity costsincurred,are considerable.To learn more from these amazing innovators, watch the completeepisode.
To take thepolarizing-foodanalogy further,maybe you don’t like Brussels sprouts because they were served boiled to mush.Try them roasted, as slaw— there are many possibilities. Good-for-youingredients can bedeliciousandnutritious!For those of you who haven’t warmed up toDOE as a vital ingredient for rapid innovation, weinvite you to give it a try and experience foryourself what accelerated learning and innovation feels like.You, too, might say, “It changed my life!”