|
FAQ
Why do green triangles appear on my half-normal plot of effects?
Original question from an Analytical Method Developer:
“I see green triangles on my half-normal plot of effects. In the legend these are identified as ‘error estimates’. Why are these popping up and what do they mean?”
Answer:
Your question is very timely, coming in just a few days before the year-end holidays. Thus, one explanation is that it being the holiday season, our software decorates the half-normal plot with Christmas trees. Several years ago (Dec. 3, 2020) Shari Kraber displayed this seasonal spirit in her blog on "Christmas Trees on my Effects Plot?" As she explained and illustrated, these triangles appear when your design includes replicates that produce pure error. See her blog for the real story (no, our programmers did not code in the Christmas trees as a seasonal decoration).
Heads-up: Sometimes, but not often, you will see green triangles even though the design does not include replicates: They represent unused degrees of freedom not used to estimate an effect. In any case, these triangles come in very handy to identify the near-zero effects that should not be selected. For example, Shari provides a great illustration where they make it clear that no effects fall off the line of normal variation and thus none should be selected. Unfortunately, this happens more often than experimenters would like—nothing is significant due to too much variation, testing the wrong factors and/or not setting their levels far enough apart to generate big effects.
One other thing to watch out for: the line of green triangles coming up noticeably steeper than the trivial many effects shown by the orange and blue squares. This may indicate a significant lack of fit. I discussed this in FAQ 2 of my Volume 5, Number 8 DOE FAQ Alert. If you are not already suffering from too much information (‘TMI’), check out my advice to the questioner—a method developer like you.
(Learn more about selecting significant effects by enrolling in the next Modern DOE for Process Optimization.)
|
|
|
EVENTS
I will present two webinars in February for professional societies:
- “Deploying DOE to identify vital factors that affect quality” on February 7 at 1 pm US Central Time, sponsored by the American Society for Quality (ASQ) Statistics Division. Reserve your seat via the link here.
Click here to view the complete list of Stat-Ease events.
Do you need a speaker on DOE for a learning session within your company or professional society at regional, national, or international levels? If so, please get back to me.
|
|
ONLINE LEARNING
Sharpen up your DOE skills with a mix of free and paid training: whatever fits your business needs.
A gift to my DOE FAQ Alert subscribers: use the coupon code 100NP to get an additional $100 discount on our February/March paid DOE courses.
Comprehensive DOE courses — Online instructor-led learning
See this web page for the complete schedule of upcoming Stat-Ease courses. To enroll in the workshop that suits you best, click Register on that page, or click here to contact us.
If you lead a group of 6 or more colleagues, save money and customize content via a private workshop. For a quote, please contact us.
Free webinars — Sign up now to take advantage
On April 17 I will present Exploiting Statistical Experiment Design to Accelerate Pharmaceutical R&D. Learn how multicomponent and multifactor design-of-experiment (DOE) tools empower experimenters to quickly converge on the quality by design (QbD) “sweet” spot—ingredient and factor settings that meet all specifications at minimal cost. All examples come directly from pharmaceutical industries.
|
|
BLOGS
StatsMadeEasy Blog
My wry look at all things statistical and/or scientific with an engineering perspective.
Stat-Ease Blog
Great tips from the Stat-Ease team for making DOE easy, for example, this recent posting by me on Know the SCOR for a winning strategy of experiments.
|
|
Feel free to get back to me via [email protected] with further questions or comments: I would really appreciate hearing from you!
All the best,
Mark J. Anderson, PE, CQE, MBA
Engineering Consultant, Stat-Ease, Inc.
www.linkedin.com/in/markstat/
|
|
|
“The world's best statistical analysis cannot rescue a poorly planned experimental program.”
—Gerry Hahn, N. Doganaksoy, The Role of Statistics in Business and Industry, Wiley 2008.
|
|
|
Stat-Ease, Design-Expert and Statistics Made Easy are registered trademarks of Stat-Ease, Inc.
Circulation: Over 2500 worldwide
|
|
|
|
