Here's another set of frequently asked questions (FAQs) about doing design of experiments (DOE), plus alerts to timely information and free software updates. If you missed the previous DOE FAQ Alert, please click on the links at the bottom of this page. If you have a question that needs answering, click the Search tab and enter the key words. This finds not only answers from previous Alerts, but also other documents posted to the Stat-Ease web site. Feel free to forward this newsletter to your colleagues. They can subscribe by going to http://www.statease.com/doealertreg.html. If this newsletter prompts you to ask your own questions about DOE, please address them via mail to:[email protected]. For an assortment of appetizers to get this Alert off to a good start, see these new blogs at http://statsmadeeasy.net: Yesterday the citizens of our United States exhibited their mercurial mood by voting for a transit in their political landscape from the right to the left. Today they can see the planet Mercury transit the sun. This happens only about every decade. For an astronomer's eye view (Kitt Peak, Arizona), see the webcast from 11 am to 4 pm PST by San Francisco's Exploratorium at http://www.exploratorium.edu/transit/. I expect that they will save the record of this astronomical event if you miss Mercury actually in transit this time around. 1. Newsletter Alert: The December issue of the Stat-Teaser features "The 10 Most Common Designed Experiment Mistakes" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1. Newsletter alert: December issue of the Stat-Teaser features "The 10 Most Common Designed Experiment Mistakes" Many of you will soon receive a printed copy of the latest Stat-Teaser, but others, by choice or because you reside outside of North America, will get your only view of the December issue at http://www.statease.com/news/news0612.pdf. This issue of the Stat-Teaser features an article contributed by independent consultant Jeff Hybarger with his 10 tips for avoiding the most common designed experiment mistakes. Jeff believes that as many as 90% of DOE failures can be avoided by watching out for these pitfalls. *See http://www.statease.com/soft_abs.html for details and link from there to free 45-day fully-functional trials of version 7 of Design-Expert software. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2. Expert-FAQ: Why mixture experiments exhibit low power (link to published article) -----Original Question-----
From: Mark Bailey, Statistical Consultant, SAS "I congratulate you and Pat on the wonderful paper 'Interpreting Power in Mixture DOE — Simplified' that appeared the latest issue (Vol. 25, No. 1) of the ASQ Statistics Division newsletter. (See http://www.asqstatdiv.org/documents/newsletters/Fall06StatDiv.pdf.) Many members are involved in experiments with mixture components. This issue of power is often not apparent to the practitioner who faces constraints for the first time. Pat does a real service to these experimenters by raising their awareness and arming them with an understanding and a solution. Also, the explanation is so clear and straightforward. I especially like his choice of the pedagogical example and his use of graphics, so that it is immediately clear what the fundamental issue is about. You demonstrate that even with low power for estimation and hypothesis tests, prediction variance is still acceptable. I wonder what you think of another direction. What about removing the 'quadratic' mixture effect from the model, since the contribution, as shown by the graphic, is so small in the first place. Would this change affect the power for the better?" Answer: A 7.1 % These power results are only marginally better than those for the same terms when evaluated as part of the quadratic mixture model. The problems stem from this formulation region being restricted to such a small sliver of the triangular mixture space (unconstrained). Ironically, although component C is the one that's severely constrained, A and B apparently pay the price by being 0.995 correlated according to Pearson's r for factors. This mini-paper explains the problem, but Pat has only recently come up with a possible solution which he plans on unveiling at the 2007 Quality and Productivity Research Conference in a talk titled "A Mixture Design Planning Process" that will be co-authored by our advisor, Professor Gary W. Oehlert (School of PS. I thank Mark Bailey for the heads-up on this month's quote, which supports Pat's graphical approach to explaining this power puzzler. (Learn more about mixture design by attending the three-day computer-intensive workshop "Mixture Design for Optimal Formulations." For a complete description of this class, see http://www.statease.com/clas_mix.html. Link from this page to the course outline and schedule. Then, if you like, enroll online.) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3. Info alert: Link to newly-published article on DOE and response surface methods (RSM) in Chemical Processing The November issue of Chemical Processing magazine features an article by me and Patrick Whitcomb titled "Rethink experiment design." It makes a case for letting go of OFAT in favor of multivariable testing via DOE/RSM and provides a heads-up to minimum-run designs that make it easier than ever before to optimize many process factors. See this publication at http://www.chemicalprocessing.com/articles/2006/166.html. -----Unsolicited Compliment----- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4. Information sought: Application of DOE to drug discovery -----Original Question----- "We are engineers on a Product Development Team that is developing a new non-systemic/plasma drug delivery system. The pharmacokinetic scientists on the Team have no understanding of Design of Experiments (statistical designs). To determine the dose response and toxicological impact of a drug, they have been trained to evaluate only drug concentration and volume, one variable at a time. However, drug infusion rate and length of infusion time are two independent variables (we can vary them significantly) that we know will produce different dose response/toxicology results, even if the resulting volumes are the same. So we'd like to run a three-factor design (concentration, flow rate and time). Can anyone share their experiences in doing a DOE like this in the drug discovery process specifically for dose response or toxicology studies? We need "expert opinions" or case studies to help demonstrate that DOE is a viable alternative."
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5. Reader response: Getting a list of DOE FAQ's -----Original Question----- Answer: PS. Purchase Dr. Montgomery's "Design and Analysis of Experiments," 6th Edition via the Stat-Ease e-commerce site at http://www.statease.com/prodbook.html ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 6. Events alert: Do you seek a speaker on DOE? Click http://www.statease.com/events.html for a list of appearances by Stat-Ease professionals. We hope to see you sometime in the near future! PS. Do you need a speaker on DOE for a learning session within your company or technical society at regional, national, or even international levels? If so, contact me. It may not cost you anything if Stat-Ease has a consultant close by. However, for presentations involving travel, we appreciate reimbursements for ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ If you work near the West Coast (or want to visit there this winter) and you want to get going on DOE, attend our three-day computer-intensive "Experiment Design Made Easy" workshop See http://www.statease.com/clas_pub.html for schedule and site information on all Stat-Ease workshops open to the public. To enroll, click the "register online" link on our web site or call Stat-Ease at 1.612.378.9449. 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.* Call us to get a quote. *Believe it or not, it only takes a class of 4 students to make it economical for Stat-Ease to come and teach at your site versus sending them out to one of our public presentations. The economics are detailed in the July 2006 issue of the Stat-Teaser newsletter at http://www.statease.com/news/news0608.pdf. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ I hope you learned something from this
issue. Address your general questions and comments to me at: [email protected].
Sincerely, Mark Mark J. Anderson, PE, CQE PS. Quote for the month — why it's good to visualize data: Acknowledgements to contributors: ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Interested
in previous FAQ DOE Alert e-mail newsletters? Click here to add your name to the DOE
FAQ Alert newsletter list server.
|
|
Stat-Ease, Inc.
2021 E. Hennepin Avenue, Ste 480
Minneapolis, MN 55413-2726
e-mail: info@statease.com
p: 612.378.9449, f: 612.378.2152