Issue: Volume 4, Number 8
Date: August 2004
From: Mark J. Anderson, Stat-Ease, Inc. (http://www.statease.com)

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 previous DOE FAQ Alerts, 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:StatHelp@StatEase.com.

I just returned from Southern California where I gave a talk to the Society of Industrial Microbiology in Anaheim. My two teenage daughters came along to visit Disneyland. Coincidentally, earlier this month The Dallas Morning News reported that the record for doing Disney is now 10 hours and 40 minutes. It was set by Rich Vosburgh, an IT guy from Dell Computer. Here's an interesting statistic from the article: The number of alternative travel schedules for 20 attractions, only half of the number in Disney's Magic Kingdom, exceeds 50 million billion combinations, or six times the number of grains of sand on Earth! To learn how Vosburgh selected the optimal route, copy and paste this web site path into your Internet browser: www.mickeynews.com/News/DisplayPressRelease.asp_Q_id_E_744Day, or click on this link— http://makeashorterlink.com/?Y2FC643F8.

What I liked best about this story is that it took advantage of statistics. Data collectors made numerous laps around Disney. The article points out that "..With each lap ...[the]... program becomes more powerful. With more data to average, [it] has a better idea how long a visitor would have to wait to ride Splash Mountain at 2:30 p.m. on a holiday weekend in July. Answer: about 135 minutes." My girls waited over 60 minutes at Splash Mountain, but then it broke down. I wonder what the odds are of this happening?

Here's what I cover in the body text of this DOE FAQ Alert (topics that delve into statistical detail are designated "Expert"):

1. FAQ: A predictive model for one factor with many levels
2. Info alert: See a new article on DOE to reduce "frog spots" in semiconductor wafers; also mixture design for coatings
3. Reader reply: Fun experiments for adults and children
4. Events alert: Talk in Toronto at the Joint Statistical Meetings
5. Workshop alert: "Experiment Design Made Easy" is coming to Philadelphia

PS. Quotes for the month
—Provocative statements from two new books on statistics.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

1. FAQ: A predictive model for one factor with many levels

Question
From: Ohio

"I have a question regarding the ANOVA output from Design-Expert® software. I have a designed experiment where one of the factors (E) has six levels and it's a categorical factor. When I get the ANOVA table, in the equation part this factor only has five terms in addition to the overall intercept. Does this
have to do with degrees of freedom or something?"

Answer:
Yes. It's a classic math problem that usually involves basketball players. For example, you're given the mean height of five players, those of four individually and asked how tall the fifth must be, which of course can be worked out by difference.

The models for multicategoricals get very messy, especially with more than one factor, so you'd best not look at them but rather make use of the effects plots, which show the predicted means and least significant differences (LSD).

Stat-Ease consultant Shari Kraber contributed this explanation:
"In a two-level design, the coefficient represents the one slope between the two levels. For a six-level factor, five slopes are quantified via five coefficients. Unfortunately, these coefficients cannot be interpreted in a straight-forward manner."

Stat-Ease consultant Pat Whitcomb provides this detail in training materials* on how Design-Expert models the main effect from a categorical factor:
"The first coefficient is the difference between the overall mean and the mean for the first level of the treatment. The second coefficient is the difference between the overall mean and the mean for the second level of the treatment, and so on. The negative sum of all the coefficients is the difference between the overall mean and the mean for the last level of the treatment."

*(Learn more about factorials with categoricals by attending the three-day computer-intensive workshop "Experiment Design Made Easy." See http://www.statease.com/clas_edme.html for a course description. Link from this page to the course outline and schedule. Then, if you like, enroll online.)

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

2. Info alert: See a new article on DOE to reduce "frog spots" in semiconductor wafers; also mixture design for coatings

Click the following link to view an article titled "Solving Process Issues at an ASIC Fab using Design of Experiments" published in the July 2004 issue of MICRO Magazine: http://www.micromagazine.com/archive/04/07/clarke.html. See how author Carl Clarke, of AMI Semiconductor, solved two perplexing wafer production mysteries using design of experiments, thus saving the company $180,000 a year.

To view an article from Paint & Coatings Industry Magazine on mixture design titled "How to Bake the Perfect Cake", click http://makeashorterlink.com/?D275128F8. The author, Rick Roesler, worked with the three Principals of Stat-Ease—Pat Whitcomb, Tryg Helseth and me—at General Mills Chemical Division in the 1970's. These were formative years for all four of us in the field of DOE and in particular, mixture design.*

*(To master these powerful tools of DOE, attend our "Mixture Design for Optimal Formulation" workshop. For a description, see http://www.statease.com/clas_mix.html. Link from this page to the course outline and schedule. You can enroll online by linking to the Stat-Ease e-commerce page for workshops.)

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

3. Reader reply: Fun experiments for adults and children

I received many comments about my youngest daughter's taste test on colas (see http://www.statease.com/news/news0405.pdf). Here's an inquiry that inspired me to detail more experiments that might be fun for adults and children.

Original Message
From: Peter Kolesar, Professor, Columbia University

"I teach a course on quality and I am always looking for good and simple actual experiments to do with students. I also sometimes visit my daughter's science class in her elementary school—she is 11. I'd appreciate any information you could forward to me on the "kids" experiments mentioned in your article in the Stat-Teaser."

Answer:
I can see that I need to go back over all the years of experimentation with my five children (hmmm—that did not come out quite right!) and compile a list of "Mark and Katies' Favorites" (she can consult with her four older siblings-two sisters and two brothers).

See 'Katie's Favorites' and many other fun experiments in a newly revised list called "DOE It Yourself" that's posted at http://www.statease.com/pubs/doe-self.pdf.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

4. Events alert: Talk in Toronto at the Joint Statistical Meetings

Reminder: If you make it to the 2004 Joint Statistical Meetings (JSM) in Toronto, Canada in August, stop and visit Stat-Ease at booth #405. Also, sign up for the JSM RoundTable Discussion on Wednesday, August 11th on "Design of Experiments Trials and Tribulations." Stat-Ease consultant Shari Kraber will be the moderator. She says "Participate in a lively discussion of the trials and tribulations of planning and running designed experiments. Plan to share your experiences and learn from the experiences of others. Discuss the most common pitfalls that experimenters encounter and learn how to avoid them. Explore problems with fractional factorials, mixtures, missing data, pass/fail data, etc."

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!

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

5. Workshop alert: "Experiment Design Made Easy" is coming to Philadelphia

Stat-Ease will present "Experiment Design Made Easy" on August 17-19 in Philadelphia. For those of you on the East Coast of the USA, this is a great opportunity to learn DOE in your own backyard.

See http://www.statease.com/clas_pub.html for schedule and site information on this and all other 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.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

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

Sincerely,

Mark

Mark J. Anderson, PE, CQE
Principal, Stat-Ease, Inc. (http://www.statease.com)
2021 East Hennepin Avenue, Suite 480
Minneapolis, Minnesota 55413 USA

PS. Quote for the month—Provocative statements from two new books on statistics:

"Using fancy tools like neural nets without understanding statistics is like doing brain surgery before knowing how to use a band-aid."
—Larry Wasserman, author of All of Statistics (book review at http://www.maa.org/reviews/allofstatistics.html)

"No single correct, end-all and be-all answer exists. Some people say that's what they love about statistics, and some say that's what they hate about statistics."
—Deborah Rumsey, author of "Statistics for Dummies" (for details copy and paste this web site path into your Internet browser: www.dummies.com/WileyCDA/DummiesTitle/productCd-0764554239.html
or click this link—http://makeashorterlink.com/?Y11A228F8)


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
—Fellow Stat-Ease consultants Pat Whitcomb and Shari Kraber (see http://www.statease.com/consult.html for resumes)
—Statistical advisor to Stat-Ease: Dr. Gary Oehlert (http://www.statease.com/garyoehl.html)
—Stat-Ease programmers, especially Tryg Helseth (http://www.statease.com/pgmstaff.html)
—Heidi Hansel, Stat-Ease marketing director, and all the remaining staff

DOE FAQ Alert—Copyright 2004
Stat-Ease, Inc.
All rights reserved.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

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 (see above)

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

Statistics Made Easy™

DOE FAQ Alert ©2004 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
e-mail: info@statease.com
p: 612.378.9449, f: 612.378.2152