Dear Experimenter,
Here’s a fresh set of answers to frequently asked questions (FAQs) about design of experiments (DOE); plus timely alerts for events, publications and software updates. Check it out!

I hope you learn something from this issue. Address your general questions and comments to me at: [email protected].

Sincerely,
Mark J. Anderson, PE, CQE
Principal, Stat-Ease, Inc.

P.S. - Quote for the month:
A good analogy by Peter Drucker on the difficulty of prediction based on past performance (apropos for these stressful times of the COVID-19 outbreak).
[Page down to the end of this e-zine to enjoy the actual quote.]

IN THIS ISSUE
FAQ
Need more power? Replicate!

FAQ
More information on KCV designs in Design-Expert® software version 12

Webinar Alert
New-User Intro to Design-Expert Software

User Meeting Alert
June’s 8th European DOE Meeting shifted to a ‘virtual conference’

Events Alert
Check out upcoming talks by Stat-Ease

Workshop Alert
See when and where to learn about DOE—Sign up now before classes fill

 
BLOGS
StatsMadeEasy Blog
My wry look at all things statistical and/or scientific with an engineering perspective. Also, see the Stat-Ease blog here for tips on making DOE easy. For example, a recent posting provides “Background on the KCV Designs”. Check it out!
FAQ
If more power needed for a fractional factorial, why not simply replicate it?

Original question from an Engineering Consultant:
“I set up a two-level fractional factorial in DesignExpert, but its power falls below the level recommended by the program. My first instinct is to simply replicate the design. However, the program Help on Regular Two-Level Factorial Designs advises users not to replicate a fractional factorial design. Could you please explain the reason why?”

Answer from Stat-Ease Consultant Shari Kraber:
“Let's say you are starting with a 1/4 fraction design. If you replicate that, you get a duplicate of the same runs, which will increase power. However, if instead, you change to a 1/2 fraction, it provides the same number of added runs as replicating, but now you reduce the aliasing and cover more of the design space. Therefore, going to a higher fraction gives more benefit than just replicating. It increases power AND estimates more model terms AND tests more unique combinations—a much better value for the same number of added runs.”

PS. If you use Design‑Expert, see for yourself why Shari’s advice makes sense by choosing the regular two-level option for 6 factors in 16 runs (1/4 fraction), a resolution IV screening (yellow) design. Press ahead to the response screen and enter 1.1 for the Signal (overwriting the default value of 2). Press Next to see that the power falls far below the recommended 80%. Now go back to the design-builder and replicate the design by going from 1 to 2. Going forward again to power you see the expected improvement. However, as you can easily demonstrate by reverting to 1 replicate and changing the selection to the green 32-run option, this approach provides the same power but at higher resolution (V). For the same number of runs, you achieve a characterization of interactions rather than remaining stuck with only a screening for main effects. Smart!
- Mark

(Learn more about fractional factorials by attending the two-day computer-intensive workshop Experiment Design Made Easy or, better yet, extend your training to a third day and complete Modern DOE for Process Optimization.)
FAQ
The KCV designs in Design-Expert® software version 12 will be ideal for streamlining my graduate student’s upcoming mixture-process combined experiment: How can she learn more?

Original question from an Engineering Professor:
“Mark: I have a student (last one) who is working on a combined mixture-process design, and the KCV [Kowalski, Cornell and Vining] model seems like a good one to try. Is there any tutorial available for using the KCV model?  What is a good reference for this model? Any help would be greatly appreciated. We trying to cut down the runs as much as possible.”

Answer:
Good choice! Stat‑Ease Consultant Pat Whitcomb provides the statistical details on KCV and demonstrates how to set it up in this recorded webinar on Streamlined Models for Combined Mixture‑Process Designs.

(Learn more about KCV designs by attending the computer-intensive three-day workshop Mixture Design for Optimal Formulations.)
WEBINAR ALERT
New User Intro to Design‑Expert


If you are just beginning with Design‑Expert and need some orientation to its superb tools for design and analysis of experiments, go to the Stat-Ease webinar page and enroll in the next “New‑User Intro to Design‑Expert Software” by Stat‑Ease Trainer Richard Williams coming up on April 17th. Refer to our webinar site for specific times. We hope you will join us for this enlightening seminar.
USER-MEETING ALERT
June’s 8th European DOE Meeting shifted to a ‘virtual conference’ due to COVID‑19 concerns—stay tuned for select talks being presented by webinar

Due to concerns about COVID‑19’s foothold in Italy and the potential for it spreading throughout Europe, we will postpone our 8th European DOE Meeting in Groningen, Netherlands to 2022. In its stead, Stat‑Ease plans to host a series of webinars in June by the keynoters and confirmed speakers. Stay tuned for further details on this ‘virtual conference’.
EVENTS ALERT
Check out upcoming talks by Stat‑Ease
Click here for upcoming appearances by Stat‑Ease professionals.
WORKSHOP ALERT
See when and where to learn about DOE—Sign up now before classes fill

You can do no better for quickly advancing your DOE skills than attending a Stat‑Ease workshop. Our expert instructors provide you with a lively and extremely informative series of lectures interspersed by valuable hands-on exercises. Enroll at least 6 weeks prior to the date so your place can be assured—plus get a 10% “early-bird” discount. See this web page for complete schedule and site information on all Stat‑Ease workshops open to the public. To enroll, scroll down to the workshop of your choice and click on it, or email our Lead Client Specialist Rachel Poleke at [email protected]. If spots remain available, bring along several colleagues and take advantage of quantity discounts in tuition. Or, consider bringing in an expert from Stat‑Ease to teach a private class at your site.*

*Once you achieve a critical mass of about 6 students, it becomes very economical to sponsor an on-site workshop, which is most convenient and effective for your staff. For a quote, email [email protected].
“Trying to predict the future is like trying to drive down a country road at night with no lights while looking out the back window.”
 
—Peter Drucker
Stat-Ease, Design-Expert and Statistics Made Easy are registered trademarks of Stat-Ease, Inc.

Acknowledgements to contributors:
Students of Stat-Ease training and users of Stat-Ease software
Stat-Ease consultants: Pat Whitcomb, Martin Bezener, and Shari Kraber
Stat-Ease programmers: Hank Anderson, Joe Carriere, and Mike Brownson
Stat-Ease business staff: Cathy Hickman, Greg Campbell, and Rachel Poleke
—who provide such supreme support!

Circulation: Over 7500 worldwide
SUBSCRIBE
Facebook
Twitter
Website
LinkedIn
Email
Copyright ©2020 Stat-Ease, Inc., All rights reserved.

Our mailing address is:
Stat-Ease, Inc.
Broadway Place West
1300 Godward Street NE
Suite 6400
Minneapolis, MN 55413


Want to change how you receive these emails?
You can update your preferences or unsubscribe from this list.