Topics in the body text of this DOE FAQ Alert are headlined below (the expert ones, if any, delve into statistical details):

PS. Quote for the month: An alarmingly high percentage of workers are calling in sick before or after weekends.

1: Newsletter alert: The new issue of the Stat-Teaser details Design-Expert software, version 9 (DX9): Discover what’s in it for you; plus see DX9 put to good use for a financial analysis

Check out the latest issue of our Stat-Teaser newsletter via this link.  It leads with a detailing “Introducing Design-Expert® Software, v9, with Split-Plots!” and follows up with Stat-Ease Consultant Brooks Henderson's analysis on “Regressing the Rupee—Part II” that demonstrates two of DX9's new tools.  Also see our heads-up on how to “Train Your Team on DOE with a Private On-Site Workshop”—an economical and convenient option for those of you whose organizations have a number of staff needing to be tooled up on design of experiments.

Thank you for reading our newsletter.  We appreciate you passing along the link to the posting of the Stat-Teaser to your colleagues.

2: Software Alert: Version 9.0.3 of Design-Expert software released (free update for licensed users of v9)

Newly-released version 9.0.3 of Design-Expert software is posted at this download site for free trial evaluation.  To update older licensed versions of 9.0, simply download the update from within the program, or download the full installation and reinstall it.  The release primarily provides maintenance of existing features.  View the Read Me file for details on this update, installation tips, known ‘bugs,’ change history, and FAQs.

3: FAQ: Center points in experiments that include one or more categorical factors

Original question from a Statistician/Quality Engineer:
“One of our scientists used your software to design an experiment.  Some of the factors are categorical in nature.  He included center points in the design.  We noticed that typically the program doubled the number of center points for the categorical factors.  Why does it do this?”

Answer from Stat-Ease Consultant Shari Kraber:
“At each combination of the categorical factors Stat-Ease software will put in the number of center points requested.  For example, for one two-level categorical the center points will be located at the mid-levels of the numeric factors at both categorical levels, that is, they will be doubled.  As you increase the number of categorical factors the number of center points multiply exponentially.  We advise experimenters to first determine the best categorical combination in a screening design.  Then after narrowing the field to a vital few numeric factors, add center points to the second experiment.  Otherwise you can:

• Reduce the number of center points to three or two per categorical level.
• Edit designs with too many center points so they feature them only at the categoric combination that is of most interest.”

P.S.  Learn more about this frequently-asked question by reading “Too many center points!”, Brooks Henderson & Pat Whitcomb, FAQ #4 of DOE FAQ Alert V10, No: 10 (Oct 2010) posted here. —Mark

4: Expert-FAQ: Must factor levels really be reset in split-plot designs?

Original Question from Albert Plant, Trainer and Consultant in Design of Experiments:
“[Albert Plant, based in Ireland, is a chartered mechanical engineer with a degree in statistics.  He provides training and consultancy on a range of statistical tools including, of course, design of experiments, but also statistical process control, sampling, gauge R&R, and general statistics.  He wrote his first design of experiments training course in 1995 and began using Design-Expert software around 1999 with version 5.  Albert reports that Ireland is the home for a number of leading multinational pharmaceutical and medical device companies, many of them American, which provide the main customer base for his training and consultancy work.  He also works across all manufacturing sectors including automotive, electronics, and specialist, some whose R&D staff he has trained in DOE with Design-Expert.]

“Reading the “Must we randomize our experiment” in your StatsMadeEasy blog of 12/31/13, I am motivated to ask you about the relationship between randomization and resetting of the factor levels at each run.  My understanding is that, if possible to do so, there are two particular things (among several others, of course) that you should ensure happens when designing and running the experiment:

1. The experimental runs should be randomized—this is readily done in Design-Expert.
2. The factor levels should be reset for each experimental run—usually resisted by experimenters in my experience!!

So in addition to randomization, you should also reset the factor levels—have I got that right?  If so, when we look at the possibility of using split-plot designs to deal with hard-to-randomize designs, what about item 2 above, the resetting of the levels?  Even if we use split plots to deal with the issue of randomization, should the factor levels still be reset in a split plot or does this design just deal with the randomization issue?  In other words, are issues 1 and 2 essentially separate and, if possible, both should occur?”

Answer:
Yes, in addition to randomizing runs, experimenters should also reset the factor levels.

A split-plot structure makes this a lot trickier.  The advice above still holds but for the hard-to-change (HTC) factor(s) the reset occurs between groups.  For example, let’s say oven-temperature is the HTC; then groups of temperature occur in a random pattern, for example, group 1 low temperature–>group 2 high temperature–>group 3 high temperature–>group 4 low temperature… and so forth.  As tempting as it would be just to keep on the same high temperature setting between groups 2 and 3, the experimenter must reset the temperature to get an accurate measure of error.

(Learn more about split plots by attending the half-day computer-intensive workshop Factorial Split-Plot Designs for Hard-to-Change Factors (FSPD).  Click on the title for a description of this class and link from this page to the course outline and schedule.  Then, if you like, enroll online.)

5: Book giveaway: Enter drawing for a free DOE or RSM Simplified book.  You might win!

(Sorry, due to the high cost of shipping, this offer applies only to residents of the United States and Canada.)

Simply reply to this e-mail by May 26 if you’d like a free DOE (1 copy) or RSM (5 copies) Simplified book.  These are either slightly used after being exhibited or flawed immaterially to an extent that they cannot be sold. Some books may be missing CDs, but, if so, we can provide a download of the software.  The co-authors—Pat Whitcomb and me—have signed them.  Who wouldn’t want an autographed copy of a statistics book?!

After a great deal of calculating, the two of us have come to the conclusion that your odds of winning are nil if you do not enter this drawing. ; )

P.S. Consider as a companion to the DOE Simplified book our audiovisual (voiced-over Powerpoint presentation) Launch Pad described here.  Watch this for free and then consider whether to pay a modest fee for engaging Stat-Ease Consultants on answering questions, correcting answers to problems and so forth in return for earning 1 CEU.

6: Webinar alert: “I really would rather not randomize my experiment!!!”

In this webinar titled “I really would rather not randomize my experiment!!!” (repeated three times for your scheduling convenience), Stat-Ease Consultant Wayne Adams discusses the pros and cons of restricting the randomization of an experiment.  He provides practical advice on how to properly screen and characterize hard-to-change (HTC) factors (for example oven temperature) via factorial split-plot designs—a new feature provided by Version 9 of Design-Expert (DX9).  Reserve your Webinar seat now by clicking one of the links below:

1. Monday, June 9th  at 8 pm USA-CT* for eastern Asia and Oceania (others welcome!),
2. Tuesday, June 10th at 6:30 am USA-CT* for Europe, Africa, Middle East and western Asia (others welcome!),
3. Wednesday, June 11th at 11 am USA-CT* for the Americas and Caribbean (others welcome!).

If this is your first Stat-Ease webinar, please review these suggestions on how to be prepared.  If questions remain, direct them to our Communications Specialist, Karen Dulski, via [email protected].

*(To determine the time in your zone of the world, try using this link.  We are based in Minneapolis, which appears on the city list that you must manipulate to calculate the time correctly.)

7: Events alert: Cleveland Coatings Conference (short-course on mixture design), Joint Research Conference in Seattle, 5th European DOE User Meeting in UK (final notice)

At the Technical Symposium of the Cleveland Coatings Society June 3rd I will present a 2-hour short-course on “Statistical Design of Experiments (DOE) for Optimal Formulation of Coatings”—see details here.

Consultant Pat Whitcomb will give a talk on “Split Plots Pros and Cons” at the Joint Research Conference, co-sponsored by the American Statistical Association (ASA) sections on Physical and Engineering Sciences as well as Quality and Productivity.  These groups come together every four years or so, making this a very special event.  This year the joint conference will be held at the University of Washington in Seattle—see more details on it here.  If you can make it, please stop by the Stat-Ease exhibit and visit with Pat and/or Consultant Shari Kraber who will also attend this statistical conference.  If you haven’t seen v9 of Design-Expert yet, ask for a demonstration.

[Final Notice] We are pleased to announce the 5th European DOE User Meeting July 10-11 in Cambridge, UK, co-sponsored by PRISMTC.  See further details on the event at their conference site here, including information about pre-meeting DOE workshops.  Space is limited for the meeting itself and local lodging in particular, so you are advised to make your plans as soon as possible.

Click here for a list of upcoming 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, or if a web conference will be suitable.  However, for presentations involving travel, we appreciate reimbursement for travel expenses.  In any case, it never hurts to ask Stat-Ease for a speaker on this topic.

8: Workshop alert: DOE classes coming to New Jersey!

All classes listed below will be held at the Stat-Ease training center in Minneapolis unless otherwise noted.  If possible, enroll at least 4 weeks prior to the date so your place can be assured.  Also, take advantage of a $400 discount when you take two complementary workshops that are offered on consecutive days.

• Experiment Design Made Easy (EDME)
  
• June 16-17, New Jersey*
• August 5-6
  
  
• Factorial Split-Plot Designs for Hard-to-Change Factors (FSPD)
  
  • August 7 (half day)
    
    
• Response Surface Methods for Process Optimization (RSM)
  • June 18-19, New Jersey*

*Take both EDME and RSM in the same week to earn $400 off the combined tuition!

• Mixture Design for Optimal Formulations (MIX)
• August 18-19, New Jersey
• November 4-5**
  
  
• Advanced Formulations: Combining Mixture & Process Variables (MIX2)
• November 6-7**

** Take both MIX and MIX2 to earn $400 off the combined tuition!

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 call Rachel 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].

Please do not send me requests to subscribe or unsubscribe—follow the instructions at the end of this message. Sincerely,

Mark

Mark J. Anderson, PE, CQE
Principal, Stat-Ease, Inc.
2021 East Hennepin Avenue, Suite 480
Minneapolis, Minnesota 55413 USA

PS. Quote for the month—An alarmingly high percentage of workers are calling in sick before or after weekends:

 
"40% of the sick leaves are on a Monday or Friday.  This must change.”

—The Pointy Haired Boss from a Dilbert cartoon by Scott Adams.  (According to this study on the role of extended weekends in sickness absenteeism it’s actually a lot worse than the Boss thinks—rates of sick leave for Mondays and Fridays being 1.4 and 1.9 times greater than those for other weekdays. —Mark)

Trademarks: Stat-Ease, Design-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, Shari Kraber, Wayne Adams and Brooks Henderson
—Statistical advisor to Stat-Ease: Dr. Gary Oehlert
—Stat-Ease programmers led by Neal Vaughn
—Heidi Hansel Wolfe, Stat-Ease sales and marketing director, Karen Dulski, and all the remaining staff that provide such supreme support!

For breaking news from Stat-Ease go to this Twitter site.

DOE FAQ Alert ©2014 Stat-Ease, Inc.
Circulation: 6300 worldwide
All rights reserved.