In this Issue

-----

From the Publisher

Our circulation has nearly doubled as a result of the last two issues.  Thanks for your support.

Here is our sleepy summertime issue, though it is not quite as sleepy as we thought. June has been a frantic month with two very successful classes, two major software updates, and many changes to the web site.

I hope you are not disappointed that our lead article is so mainstream this month. I was unable to lure any of my colleagues into writing an inflammatory article this month. Certainly, I would like to solicit articles from anyone who would like to take a provocative stand on a DOE.

Our number one goal is to encourage discussion and the exchange of ideas on new directions in DOE.

Speaking of which, we had a great letter from Greg Piepel in response to Ron Schoenberg's article. Check it out in our new letters to the editor section. Many thanks to Greg and particular thanks to Ron Schoenberg who was willing to be a lightening rod to get this discussion started. We also had several supporting letters from people that said it is about time that somebody pointed out that there are many situations where screening is not the primary concern.

Check out these articles and more through our on-line archives:
http://www.processbuilder.com/doe/Newsletters/Default.htm

Table of Contents

----------------------------------

What is DOE?

by William D. Kappele

DOE stands for "Design Of Experiments." DOE helps you to design an experiment that will provide you with the most information possible with the least amount of work. Everyone wants to perform experiments that provide a lot of valuable information with as little work as possible. So why doesn't everyone use DOE?

Different people have different reasons for not using Design of Experiments. Let's take a look at three of them.

  1. "I have never heard of DOE." Many engineers and scientists leave college without any exposure to Design of Experiments. They are taught to vary one factor while holding the others constant. This is an inefficient and misleading way to perform an experiment, but it is what many colleges teach.  Now that you've heard of DOE, you can take advantage of its power to make yourself a top performer.
  2. "Great, I can design an experiment, but I don't know how to analyze it to get the information out of it." Using a designed experiment allows you to collect the data required to gain the most information with the least work, but it doesn't tell you how to get that information out of the data. For that, you need Response Surface Methodology (RSM). Although this sounds scary, the modern DOE software like STRATEGY provides user-friendly analysis using Response Surface Methodology. RSM provides you with maps of what your experimental system is doing. You can use these maps to find the best combination of factors for your work -- the combination that gives you the best responses.
  3. "The math is much too hard. I'm not that good at math." Most modern DOE software handles all of the math complexities for you. You don't have to deal with them. Unfortunately, many training courses teach you the mathematics even though you won't use it in your work. This can scare people away from using DOE.

Design of Experiments will get you the answers you need as efficiently as possible. When you begin using DOE, you'll wonder how you ever worked without it.

The class, "A Modern DOE Workshop," was specifically designed to teach you practical DOE. You learn to apply DOE using software, not math.

--

Bill also writes a great newsletter, E-Math News. You can subscribe to it at <http://www.MathOptions.com>.

Table of Contents

----------------------------------

Short Class Notes & Schedules

Our last public introductory class of the summer starts in just a little over two weeks in Union City, CA. Get your registrations in ASAP so that you do not miss out on this opportunity.

Note that we have changed the date and time of the next class in New England.

July 20, 21, 22

Performing Objective Experiments
Union City, CA
http://www.mathoptions.com/DOE%20Training.htm

August 27

Basic Statistics for Industry
Anacortes, WA

Sep 9, 10

Advanced DOE Workshop
Boulder, CO
http://www.processbuilder.com/doe/Classes/mixtures.htm

Week of September 20

A Modern DOE Workshop
Sturbridge, MA
http://www.processbuilder.com/doe/Classes/performi.htm

All of these courses are available in-house. Drop me a line (mailto::abcorwin@processbuilder.com) for more information. We are also looking for instructors to teach our class in Europe, Australia/New Zealand, and South America. Please contact me if you have any such interest.

Table of Contents

-----------------------------------

Web Site Updates

Our web site continues to grow apace. Thank you all for your many suggestions. The wealth of information available on the net continues to grow at a phenomenal pace, and we need all of the help we can get to keep on top of it.

Most of the maintenance has been to the DOE links section of our site. We have added hundreds of new links, and we have done considerable reorganization to make it easy to navigate the increasing flood of information. New in this section pages on professional societies useful to experimenters, journals, papers, etc. This has cleaned up our miscellaneous DOE links page considerably and, we hope, has made it more useful.

Please look over these changes and let us know what you think.

http://www.processbuilder.com/doe/Links/default.htm

Table of Contents

-----------------------------------

Software Updates

STRATEGY (11.4) is now available on the Process Builder web site.

This version features improved overlay charts, and it eliminates the problems caused by changing the number of responses in the model file. In addition, all of the special plot printing functions have been optimized.

Users of Windows NT 4.0 will find this version much more robust and reliable.

This is available through the following web page:

http://www.processbuilder.com/doe/Software/strategy/downloads.htm

Table of Contents

-----------------------------------

STRATEGY Tip -- Using the Overlay Charts

One of the features that we have upgraded in STRATEGY recently is the overlay plots. They are an excellent tool for showing the sweet spot to customers and management.

As always, we recommend that you find your best sweet spot using GridSearch. (In fact, the overlay plot feature requires that you have a valid GridSearch.)  Plots are wonderful tools, but they are not exactly the most efficient tool for finding a sweet spot when you have more than two factors and more than one response. As a matter of fact, if you have a relatively simple experiment with four factors and three responses, you would have to make 867 contour plots to find the sweet spot. Clearly, plots are impractical for this purpose, but they are still effective at displaying your results.

Once you have run a GridSearch, generate the contour plots data files.  There are several things that you must do to show the desired sweet spot.

  1. Select the factors that you want to show on the axes. In most cases, these should be process rather than mixture factors, and you should neveruse discrete factors on an axis.
  2. Set the factor levels for the remaining factors. These should be the levels shown for the sweet spot in the GridSearch results.
  3. On the Special Tab of the Contour Plot Definition form, select "Use GridSearch Omitted Factors, Linear and Spherical Constraints"
  4. Generate the plot data files.
  5. When the list of plots appears, select a set of Matching Data files, i.e. the Remaining Factor Levels must be identical for each chart in the set.
  6. Click the Overlay Button. An overlay chart will appear showing the sweet spot area in white. The non-sweet spot area will be dark.

Note that the Overlay Button will be grayed out if you have not run a GridSearch, if you did not check the box on the Special tab, or if the Remaining Factor Levels do not match.

Table of Contents

-----------------------------------

Upcoming Conferences

Fourth International Conference on Industrial and Applied Mathematics

July 5 -- 9
Edinburgh, Scotland

For additional information, see the ICIAM 99 Web site at
http://www.ma.hw.ac.uk/iciam99/

---

Third Annual BEYOND THE FORMULA

A Statistics Conference for Mathematics Teachers Teaching Introductory Statistics

"How modern technology is affecting the teaching and learning of statistics, and how this technology can best be incorporated into the classroom."

When:

August 5, 1999; 8:30 AM to 4:30 PM and 6:30 PM to 9:00 PM
August 6, 1999; 8:30 AM and ends at 3:00 PM

Where:

Monroe Community College, Rochester, New York

General sessions:

Robin Lock, St. Lawrence University:
Opening Keynote: "How has technology changed the teaching of statistics?"
Closing Keynote: "Where do we go from here?"

Roxy Peck, Cal Poly:
"An Eclectic Approach to Teaching Introductory Statistics -- Integrating Multiple Pedagogies"

George Cobb, Mount Holyoke:
"Course content: The clothes are there, but is the emperor wearing them?"

Gordon Black, Harris Black:
"The Advent of Internet Research: A Replacement Technology"

Patty Cyr, Eastman Kodak:
"What should you know about your data to draw the proper conclusions?"

Breakout sessions:

Rick Cleary, Cornell University:
"Perceptions of Randomness"

Kunita Cooper, Minitab Inc.:
"Basic's of MINITAB"
"Using MINITAB in the classroom"

Fred Djang, Choate Rosemary Hall, Connecticut:
"Introduction to TI-83"
"Utilizing the TI-83"

Robert Heckard, Penn State:
"Visualizing Statistics"
"Combining in-class activities and technology in the classroom"

Robin Lock, St. Lawrence U:
"WWW Resources for Teaching Statistics"
"Some Tasks for Evaluating Statistical Software"

David Mathiason, RIT:
"Web-based delivery: The good, the bad, and the ugly"
"Web as a Data Resource"

Gary McClelland, Univ. of Colorado:
"Seeing Statistics: A Webbook of Interactive Graphics for Visualizing Statistics."
"Breaking the 'Virtual' Metaphor: Teaching on the Web in Ways We Never Could Before"

Roxy Peck
"Visualizing Statistical Concepts: Using Statistics  Conceptual Software to Enhance Student Understanding"

J. Laurie Snell, Dartmouth College:
"Chance News and Chance Videos"

Lori Thombs, U of South Carolina:
"Elementary Statistics Laboratory Course"
"Statistics Labs: Possible Formats and Some Examples"

 Registration Fee: $125, which includes 5 meals for participant.

Limited seating, first-come basis.

 For complete information (conference, abstracts of presentations, registration, accommodations, travel) and updates, see our webpage:
http://www.monroecc.edu/depts/math/beyond1.htm

or contact Robert Johnson by E-mail:
RJohnson@MonroeCC.edu

Phone: Dept. Office: 716-292-2930
Fax: Dept. Office: 716-292-3874

Post:
Dept. of Mathematics
Monroe Community College
Rochester, NY 14623

----

Materials Research Society

Fall 1999 Meeting
November 29-December 3
Boston, MA
http://dns.mrs.org/meetings/fall99/

---

ISI Calendar of Events

http://www.cbs.nl/isi/calendar.htm

 

Table of Contents

------------------------------------------------------------------

Thanks for your attention.

Sincerely yours,

Al Corwin
President
Process Builder

<http://www.processbuilder.com/doe/>

abcorwin@processbuilder.com