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: 1. Announcement: Version 7.1.3 of Stat-Ease software released — it features an upgrade to the FDS design-evaluation plot 1. Announcement: Version 7.1.3 of Stat-Ease software released — it features an upgrade to the FDS design-evaluation plot Version 7.1.3 of Design-Expert® (DX) and Design-Ease® (DE) software is now posted at http://www.statease.com/soft_ftp.html for a free fully-functional 45-day trial. This web site also provides patches to update older, licensed, versions of 7.1. The new release primarily addresses maintenance issues. However, it also includes a new tool for the "fraction of design space" (FDS) graph, which DOE guru Doug Montgomery says will be "very valuable in studying the potential performance of a design." It is simple 2. Newsletter Alert: July issue of the Stat-Teaser offers an enlightening article on preventing over-selection of effects 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 July issue at http://www.statease.com/news/news0706.pdf. It features an article by me titled "Bonferroni Draws the Line on Over-Selection of Effects." It shows how an unwary user can easily select too many effects from a half-normal plot. However, by making use of the Pareto plot in Stat-Ease software and paying heed to the Bonferroni-corrected threshold for statistical significance, experimenters can curb a natural bias for picking ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3. FAQ: Nominal versus ordinal choice for categorical factors
-----Original Message----- Answer (from Stat-Ease Consultant Pat Whitcomb): "Nominal coding is the default for categoric (named) factors, such as black versus white. Ordinal can only be applied to factors with discrete numeric levels, for example, three temperatures in degrees C — 0 (freezing), 20 (ambient) and 100 (boiling hot). The choice of coding affects only the coefficients — not model significance or fit. For a two-level factor there is no difference between the two. That's the simple answer. Here's a bit more explanation on the statistical aspects. Nominal coding compares the average at each level of the factor to the overall mean, whereas ordinal coding breaks the same factor sum of squares into orders — linear contribution, quadratic contribution, etc, depending on the number of levels. For more detail, including examples showing the coding, go to Help and search on 'ordinal' for the topic titled 'Factor coding in factorial designs.' To reiterate, so far as model fit and optimization are concerned these coding choices make no difference. It comes down to personal preference for certain statisticians who may be accustomed to seeing coefficients one way versus the other. Of course it is always better to be explicit by entering the value for a numeric level, for example, the numbers 0, 20 and 100 instead of the words 'Low, 'Medium' and 'High.'" (Learn more about factorial design by attending the three-day computer-intensive workshop "Experiment Design Made Easy." See http://www.statease.com/clas_edme.html for a description of this class and then link from this page to the course outline and schedule. Then, if you like, enroll online.) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4. Info Alert: Publish your DOE success story — inspirational case-study articles sought for all industries! Stat-Ease is searching for individuals or teams willing to share their success stories. Anyone who has designed an experiment that has led to improvements in their products or processes is invited to contact us. Don't worry if it didn't go perfectly, as long as you learned something about the subject of interest. Perhaps you saved the company some money, or were able to make a product that met or surpassed customer requirements. We can team you up with a technical writer who will coordinate the creation of the magazine article. You provide the interesting information and the technical writer provides the format. Plus, **************************************************************** (Jennifer was quoted by technical writer Richard Burnham in an inspiring and informative article "Engineers as Credible Marketers" published by The Business to Business Marketer — see http://www.statease.com/pubs/eng-marketers.pdf.) 5. Events Alert: Pharma in Philly & Statistics in Salt Lake City Surprised at how many talks include DOE as a top tool for process improvement, I signed up to attend and exhibit Stat-Ease software at the Pharmaceutical Technology conference in Philadelphia, PA, this month — July 24-26. For more information on this event, see http://www.pharmtechevent.com. Also, see the latest software features demonstrated by Stat-Ease at booth 305 in the exhibition area of the Joint Statistical 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, or if a web conference will be suitable. However, for presentations involving travel, we appreciate reimbursements for airfare, hotel and meals — expenses only. In any case, it never hurts to ask Stat-Ease for a speaker on this topic. Contact [email protected] if you have an event coming up with an open slot for a presentation. 6. Workshop Alert: See when and where to learn about DOE Seats are filling fast for the following DOE classes: --> Experiment Design Made Easy (EDME) --> Mixture Design for Optimal Formulations (MIX) See http://www.statease.com/clas_pub.html for complete 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 Elicia at 612.746.2038. 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 a private workshop, which is most convenient and effective for your staff. For a quote, e-mail [email protected]. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 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 — Issues with accuracy versus precision from financial wizards trying to pin down the true values of key statistics on economic well-being: "It is better to be roughly right than precisely wrong." 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