Issue: Volume 5, Number 9
Date: September 2005
From: Mark J. Anderson, Stat-Ease, Inc. (

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

Here's an appetizer to get this Alert off to a good start:

A deceptively simple geometry problem: This game, called "Planarity," was entirely programmed in Flash*—a multimedia tool often used (and abused!) to add pizzazz in Internet Web sites. The Planarity nodes respond quickly and very smoothly, because the program executes within
your browser—no screen updates are needed. *(For a history on how this tool was developed, see

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: Why leverages are flagged in Design-Expert® software
2. Expert-FAQ: How to insert covariate data within Design-Expert
3. Info alert: Using DOE to trim plastic bonding times
4. Reader response: Tabletop hockey exercise for in-class DOE
5. Events alert: Talk and exhibit at a stat conference in the UK
6. Workshop alert: Crash Course on DOE for Sales and Marketing
7. Personal note: The story of my recovery from a heart attack

PS. Quote for the month: What to say when your experiment fails to produce desirable results


1. FAQ: Why leverages are flagged in Design-Expert® software

-----Original Question-----
From: India

"In one of my analyses using Design-Expert, the ANOVA diagnostics case statistics table shows a # symbol flagging an observation where the leverage is only 0.6. The footnote reports: '# [Obs with leverage > 2 *(average leverage).]' Could you please explain why a leverage less than one is flagged?"

Somewhat arbitrarily, Stat-Ease software flags leverages at more than twice the average for a given set of experimental runs. The average leverage equals the number of model coefficients divided by the number of runs. So, for example, if you run 10 trials on one factor* and fit a linear model with 2 coefficients (intercept and slope), the average leverage will be 0.2 and any points at 0.4 (2 * 0.2) or higher will be flagged.

If you notice this before running the experiment, consider repositioning your runs to better balance leverage and thus gain more information for the same amount of effort. If the high leverage is not observed on a completed experiment (or historical data), it is best you ensure that their results are accurate because they will unduly influence the fit of one or more model coefficients.

*PS. I am not sure how this will come through via e-mail, but for my 10-point example see the grid below where ">" represents an empty space. Obviously the 2 points at the upper right will be much more influential for fitting a line than the 8 at the lower left. They will exhibit leverage of ~0.5 versus the average of 0.2 and thus are flagged by Stat-Ease software for the attention of the statistical analyst. In this example moving some of the replicates from the left to the upper right will give a better estimate of the slope with no additional runs.


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


2. Expert-FAQ: How to insert covariate data within Design-Expert

-----Original Question-----
From: Germany

"I have downloaded the trial version of Design-Expert version 6 (DX6). I want to add a covariate for an existing design set up by DX6. I have a read the answer to your frequently asked question (FAQ) "How to contend with covariates"—FAQ number two in Volume 2, Number 11 of the November 2002 "DOE FAQ Alert" ( but I cannot understand how to use this. Could you provide instructions?"

Answer (from Stat-Ease Consultant Shari Kraber):
"To begin, create a standard design for your regular factors. In the design layout screen, right-click on the last Factor column header and choose Insert Factor. Then right-click on that new factor column-header and choose Edit Info. Type in the name of the new factor. In the spaces for the low and high settings, enter the lowest and highest values for the covariate. This sets the internal coding for the regression. Click OK.

Fill in the blank spaces with the actual covariate data (you can copy/paste if the information is stored in another spreadsheet.) Then analyze as usual, but with the understanding that if a covariate is strongly correlated to another factor, the modeling will become far more difficult.*"

*PS. For example, see Chapter 2, "Lessons to Learn from Happenstance Regression," in the book RSM Simplified (—Mark

(Learn more about modeling by attending the three-day computer-intensive workshop "Response Surface Methods for Process Optimization." See for a complete description. Link from this page to the course outline and schedule. Then, if you like, enroll online.)


3. Info alert: Using DOE to trim plastic bonding times

A researcher from Northern Illinois University's Industrial Engineering Department reports on a full factorial done on the ruggedness of a viewing lens for a cell phone. The DOE revealed an interaction between bonding time and pressure that led to reduced defects and higher throughput for manufacturing. For the details, see


4. Reader response: Tabletop hockey exercise for in-class DOE

For your information, some years ago I participated in a round-table session for teachers of DOE who developed in-class exercises. The moderator asked each of us to write up our contribution for publication. My write-up, "Tabletop Hockey Meets Goals for Teaching Experimental Design," is posted at It was seen by Ariela Gruszka of Micron Technology (Boise, Idaho) who got permission to use it for DOE training at her company. I helped her work through some issues on transforming the responses from her pilot experiments. She then sent me this note to report on actual classroom results and detail her modifications to the experiment: "The experiment went great! Our puck has one side polished (smooth side) and the other side has a diamond grit (rough side). Our metal ruler is more rigid than the plastic one." Kudos to Ariela, who literally exhibited "true grit" in adapting this in-class exercise for her mission to train colleagues in DOE.

To illustrate how to deal with non-normality via response transformations, an analysis of a tabletop hockey experiment is presented in Chapter 4 of the book DOE Simplified (detailed at This was read by Katrina M. Labude, Six Sigma Master Black Belt at Conoco Phillips, who wrote me to say: "I got your book, DOE Simplified, and stole your tabletop hockey game for our BB training class. The students love it and it’s a great teaching tool. Thanks!"


5. Events alert: Talk and exhibit at a stat conference in the UK

Stat-Ease consultant Pat Whitcomb will present a talk titled "A Factorial Design Planning Process" at the 5th Annual Conference of European Network for Business and Industrial Statistics (ENBIS), which will be held on September 14-16 at Newcastle upon Tyne in the United Kingdom. Pat's presentation, co-authored by Dan Kussman of Boston Scientific, is aimed at newcomers to DOE who need help choosing designs with the proper power to detect important effects. Stat-Ease will also exhibit at this conference. See for details.

Pat will also make a presentation to the Fall Tech Conference (FTC)* in St. Louis, Missouri on October 20-21 (see for details). Pat's talk in the Graphical Methods Session of this FTC is titled "Using a Pareto Chart to Select Effects for a Two-Level Factorial DOE." It presents a new method for using a Pareto chart of t-values so that relative effect sizes get displayed properly, thus allowing the addition of t-limits that aid in the selection of the vital few that are likely to be statistically significant. *(Co-sponsored by:
—American Society for Quality (ASQ)
—Chemical and Process Industry Division (CPID) and
—Statistics Division
—American Statistical Association (ASA)
—Section on Physical and Engineering Sciences (SPES)
—Quality & Productivity Section (Q&P).)

Click on for a list of appearances by Stat-Ease professionals. We hope to see you sometime in the near future!


6. Workshop alert: Crash Course on DOE for Sales and Marketing

Seats remain open for the inaugural Crash Course on DOE for Sales & Marketing here at the Stat-Ease training center in Minneapolis on September 29. This is a unique opportunity to hear how Dr. Paul Selden has adapted the powerful tools of statistically designed, multifactor experiments to generate sales breakthroughs. For details on this one-day seminar and a link to Dr. Selden's biography, see

See 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.


7. Personal note: The story of my recovery from a heart attack

This is old news for my family, close personal friends and immediate colleagues, but the Saint Paul Pioneer Press saw fit to publish my story of recovery from a heart attack last December, which I share with you via their posting at (do advanced search in 2005 for "silent heart attack" - must purchase to see full article) The editor, Rhoda Fukushima, got off a bit in describing my event as a "silent" heart attack, which normally goes unnoticed for months, if not years. Other than that, I think she captured my experience fairly accurately.

PS. Speaking of recovery, let's all do what we can to help those who are suffering from the aftermath of Hurricane Katrina. I vacationed last Fall in the French Quarter of New Orleans and returned this Spring to give a technical presentation at a coatings research conference. These two visits give me some sense for the huge devastation in this unique American city. It makes one appreciate such mundane things as a roof over your head, food when you hunger and water to quench your thirst—none of which should be taken for granted.


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. Quote for the month: What to say when your experiment fails to produce desirable results:

"We achieved a deferred success!"
—Mark (saw this wording advised for teachers not wanting to damage the self-esteem of their students: They must avoid labeling any child as a failure.)

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 for resumes)
—Statistical advisor to Stat-Ease: Dr. Gary Oehlert (
—Stat-Ease programmers, especially Tryg Helseth (
—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 (see above)

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

Statistics Made Easy™

DOE FAQ Alert ©2005 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