Issue: Volume 7, Number 11
Date: November 2007
From: Mark J. Anderson, Stat-Ease, Inc., Statistics Made Easy® Blog

Dear Experimenter,

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 If this newsletter prompts you to ask your own questions about DOE, please address them via mail

For an assortment of appetizers to get this Alert off to a good start, see these new blogs at
—TV show misguided in mocking triangle graphs
—The lottery of life versus death
—Treat or Trick? Drinkers punked by brewers?

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

1. FAQ: Too many blocks into too few runs each?
2. Reader Response: Breaking mixture design on beers into the individual blocks by taster to assess personal preferences
3. Webinar Alert: Sizing RSM and Mixture Designs for Adequate Precision via use of Fraction of Design Space (FDS) Plots
4. Book Giveaways: Winners announced
5. Event Alerts: Need a speaker on DOE?
6. Workshop Alert:Learn about DOE and get into the spirit of the season in Minneapolis (ideal weather for Mall shopping!)

PS. Quote for the month: Why randomize? A cautionary note from George Box. (Page through to the end of this e-mail to enjoy the actual quote.)


1. FAQ: Too many blocks into too few runs each?

-----Original Message-----
From: Saint Paul
"Whether it is a 12-run fractional or 16-run full factorial design, we will not be in a position to perform all the runs in one day. A 16-run design will be done over at least 8 days and a 12-run design will performed over 6 days time. Although we will try to maintain the external conditions the same, there could be
day-to-day variation. If that needs to be accounted for we need to generate 6 or 8 blocks. So, assuming we are blocking day-to-day variation, I lose all the two-factor interactions to the blocks. How do I work around that?"

Answer (from Stat-Ease Consultant Shari Kraber):
"When only two runs can be done per block in a two-level factorial design, it is not advisable to block at all. Simply perform the entire experiment in random order. The day-to-day variation then becomes a component of overall process variation. I advise that blocks be at least 4 runs each. This provides enough information to get a valid block effect. You should monitor and record variables that change from run to run. If they vary greatly, these external factors can be accounted for as co-variates and perhaps salvage useful results from your experiment. However, chances are good that randomization will wash them out as a biasing influence."

PS from Mark: For a primer on blocking, see the March 2000 Stat-Teaser posted at It details an experiment that my wife did with her preschool class on identification of dice as a function of the number of pips. The results, made possible by incorporating blocking in the experiment design, were a bit surprising.

PPS: The NIST/SEMATECH Engineering Statistics Handbook offers a neat explanation of blocking for two-level factorial designs at

P^3: For those who learn best by listening to a talking head, check out this free podcast by statistician Keith M. Bower at (I enjoy the Scottish accent, perhaps mellowed a bit by Keith's stint in the midwestern USA as a student at the University of Iowa.)

"Block what you can, randomize what you cannot."
George Box

(Learn more about blocking by attending the three-day computer-intensive workshop "Experiment Design Made Easy." See for a description of this class and then link from this page to the course outline and schedule. Then, if you like, enroll online.)


2. Reader Response: Breaking mixture design on beers into the individual blocks by taster to assess personal preferences

I got a lot of positive feedback* on my article detailing application of mixture design to optimal formulation of a beer cocktail ( I am happy to e-mail the data to anyone interested. Here is one exchange that relates to this month's FAQ on blocking.

-----Original Message-----
From: Brian Mullen, Process Chemist, Sherwin-Williams, Cleveland
"I recently read your article on the beer mixture design in the Stat-Teaser. If you wouldn't mind, I'd love to see the data so I could play around with the design. You had mentioned the ability to break down the analysis by block—can you give a hint on how to do this? I really enjoy the Stat-Teaser!"

Open the attached Design-Expert version 7.1 software file on my "black & blue moon" beer cocktail. Check out the entire data set as you like. Then to break it down to my #1 son Ben only—block 1, follow these instructions.

1. Click the box to the left of the first row of block 2 (my #2 son Hank) and, while keeping your left mouse-button depressed, press the button to the left of the last row in the design matrix—the final tasting by my son-in-law Ryan (block 3). Now you should see two-thirds of the layout highlighted (blacked out).
2. Move your mouse-pointer over the column of buttons to the left of these selected runs and RIGHT click to bring up a menu allowing you to Set Row Status to Ignore. The program pops up a warning about having to adjust "contrasts" for blocks—OK this.
3. Analyze Ben’s overall liking of the various beer blends.

You will see that Ben knew his brew—he liked the blend of Sam Adams Black Lager and Blue Moon (a ‘white’ wheat beer). In similar fashion you could break out the other experimental blocks individually. When I did this, I saw that my son-in-law Ryan, who hails from Milwaukee, liked Budweiser more than the other two tasters. After weaning him off milk, Ryan’s parents raised him on Miller Lite, so no wonder he preferred the bland Bud!

*PS. Here are a few outliers on the generally positive feedback. At the recent Fall Technical Conference of industrial statisticians I talked up my beer-cocktail mixture design to the fellow at my right at a speakers breakfast: Doctor mixture himself—John Cornell. He reminded me of his famous bar tending experiment detailed by "In Search of the Optimum Harvey Wallbanger Recipe via Mixture Experiment Techniques" in The American Statistician (Vol. 41, No. 3, Aug. 1987, pp. 190-194). Cornell told me that they had 15 workshop students participate in drinking varying blends of orange juice, vodka and Galliano. To limit the alcohol intake of any individual, the experiment was set up in a balanced incomplete block (BIB) structure per a design developed by Cochran and Cox in 1957, which limited the imbibing to three drinks each from a two-ounce jigger. These were randomly assigned as participants arrived at the post-workshop party. I could not top that! So then I turned to the statistician at my left, who was giving me a frown. Looking at her nametag, I noted she worked for Anheuser Busch of Saint Louis, the brewer of Bud. Oops! I suddenly wished my orange juice had a little kicker of vodka and Galliano.


3. Webinar Alert: Sizing RSM and Mixture Designs for Adequate Precision via use of Fraction of Design Space (FDS) Plots

You are invited to attend a free web conference by Stat-Ease on "Sizing RSM and Mixture Designs for Adequate Precision via use of Fraction of Design Space (FDS) Plots" at 8 AM Central USA Time on Wednesday, November 28 and again at 11 AM Thursday, November 29. See item number three in last month's DOE FAQ Alert for more details: Attendance may be limited for one or both of these two one-hour webinar sessions. Contact our Communications Specialist, Karen Dulski, via to sign up. If you can be accommodated, she will send you the link for the WebConnect and dial-in for ConferenceNow voice via telephone. Toll-free access
extends worldwide, but not to all countries.


4. Book Giveaways: Winners announced

Three copies of the newly published second edition of "DOE Simplified," autographed by me and my co-author Pat Whitcomb were given away as promised by random drawing of postcards announcing version 7.1 of Design-Ease® and Design-Expert®. Here are the winners:
—> Joseph A. Wernham, Supervisor, Material Test, Eriez Mfg., Pennsylvania
—> Nhan Huynh, Chemist, Valspar, Pennsylvania
—> Benjamin Van Auken, Process Development Engineer, Pepperidge Farm, Connecticut.

In last month's DOE FAQ Alert, I announced a drawing for books on response surface methods (RSM). These two lucky readers won a copy of first edition "Empirical Model-Building and Response Surfaces" textbooks by Box & Draper:
—> Jim Alloway, Consultant, EMSQ Associates, New York
—> F. Mitch Gallant, PhD, Director, Quality Processes, Lean Quality Department, Naval Surface Warfare Center, Indian Head Div, Maryland.

The two autographed copies of RSM Simplified went to
—> Dan Schkolnik, Sonoma Orthopedic Products, California
—> Errol Williams, Production Engineer, Aveka, Minnesota.

Congratulations to all!

(The two-part series of "Simplified" books on DOE and RSM can be ordered on line from


5. Events Alert: Need a speaker on DOE?

Click 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, 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 if you have an event coming up with an open slot for a presentation.


6. Workshop alert: Learn about DOE and get into the spirit of the season in Minneapolis (ideal weather for Mall shopping!)

Seats are filling fast for the following DOE class:

—> Experiment Design Made Easy (EDME) (Detailed at
—> December 4-6 (Minneapolis)

See 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


I hope you learned something from this issue. Address your general questions and comments to me at:



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

PS. Quotes for the month—Why randomize? A cautionary note from George Box:

"Beware the lurking variable."
—George Box

Trademarks: Design-Ease, Design-Expert and Stat-Ease 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 and Wayne Adams (see for resumes)
—Statistical advisor to Stat-Ease: Dr. Gary Oehlert (
—Stat-Ease programmers, especially Tryg Helseth and Neal Vaughn (
—Heidi Hansel, Stat-Ease marketing director, and all the remaining staff


Interested in previous FAQ DOE Alert e-mail newsletters?
To view a past issue, choose it below.

#1 Mar 01, #2 Apr 01, #3 May 01, #4 Jun 01, #5 Jul 01 , #6 Aug 01, #7 Sep 01, #8 Oct 01, #9 Nov 01, #10 Dec 01, #2-1 Jan 02, #2-2 Feb 02, #2-3 Mar 02, #2-4 Apr 02, #2-5 May 02, #2-6 Jun 02, #2-7 Jul 02, #2-8 Aug 02, #2-9 Sep 02, #2-10 Oct 02, #2-11 Nov 02, #2-12 Dec 02, #3-1 Jan 03, #3-2 Feb 03, #3-3 Mar 03, #3-4 Apr 03, #3-5 May 03, #3-6 Jun 03, #3-7 Jul 03, #3-8 Aug 03, #3-9 Sep 03 #3-10 Oct 03, #3-11 Nov 03, #3-12 Dec 03, #4-1 Jan 04, #4-2 Feb 04, #4-3 Mar 04, #4-4 Apr 04, #4-5 May 04, #4-6 Jun 04, #4-7 Jul 04, #4-8 Aug 04, #4-9 Sep 04, #4-10 Oct 04, #4-11 Nov 04, #4-12 Dec 04, #5-1 Jan 05, #5-2 Feb 05, #5-3 Mar 05, #5-4 Apr 05, #5-5 May 05, #5-6 Jun 05, #5-7 Jul 05, #5-8 Aug 05, #5-9 Sep 05, #5-10 Oct 05, #5-11 Nov 05, #5-12 Dec 05, #6-01 Jan 06, #6-02 Feb 06, #6-03 Mar 06, #6-4 Apr 06, #6-5 May 06, #6-6 Jun 06, #6-7 Jul 06, #6-8 Aug 06, #6-9 Sep 06, #6-10 Oct 06, #6-11 Nov 06, #6-12 Dec 06, #7-1 Jan 07, #7-2 Feb 07, #7-3 Mar 07, #7-4 Apr 07, #7-5 May 07, #7-6 Jun 07, #7-7 Jul 07, #7-8 Aug 07, #7-9 Sep 07, #7-10 Oct 07, #7-11 Nov 07 (see above)

Click here to add your name to the DOE FAQ Alert newsletter list server.

Statistics Made Easy®

DOE FAQ Alert ©2007 Stat-Ease, Inc.
All rights reserved.


Software      Training      Consulting      Publications      Order Online      Contact Us       Search

Stat-Ease, Inc.
2021 E. Hennepin Avenue, Ste 480
Minneapolis, MN 55413-2726
p: 612.378.9449, f: 612.378.2152