Issue: Volume 1, Number 5
(For previous issues, see below)
Date: July, 2001
From: Mark J. Anderson, Stat-Ease, Inc.
Here's another set of frequently
asked questions (FAQs) about doing design of experiments (DOE), plus alerts
to timely information and free software updates.
Before I get into the meat of this message, I offer this link as an appetizer: http://www.nasm.edu/ceps/etp/mars/MARS.html. It offers information and pictures of Mars, which on June 21 came within 42 million miles (67.3 million kilometers) of Earth, the closest since 1988. I've been viewing this celestial show with my 8-inch reflecting telescope. From this part of the world (Minnesota, USA), one can see the unusually bright Red Planet in the southern sky after sunset, close to the nearly full moon and the bright red, supergiant star Antares (which means "rival of
Mars" in Greek). For free star maps suitable for Northern or Southern Hemispheres, go to http://www.skymaps.com/downloads.html. If you think more should be done to explore Mars, check out http://www.marssociety.org/. This Internet site offers all the latest news about our neighboring planet.
As Ira Gershwin said, it's "summertime
and the livin' is easy, fish are jumpin,' and the cotton is high" so I'm
not going to work you too hard in this DOE FAQ Alert:
1. FAQ: How to analyze historical (happenstance) data with Design-Expert® software
2. Info Alert: Contributed article on a drag-racing DOE and an idea on doing DOE on fishing poles (from a reader)
3. Events Alert: A heads-up on DOE talks and demos.
4. Workshop Alert: Coming soon to Seattle
5. Believe it or not: A ballpark-sized DOE?
PS. Statistics quote for the month from Yogi Berra, baseball player and manager.
1 - FAQ: How to analyze historical (happenstance) data with Design-Expert software
"Is there a way in Design-Expert to utilize current (production) data for DOE, in other words use existing data to set up a DOE design and analyze, without doing any experimentation?"
I'm glad you asked this, because we've just added a feature that helps you do this. The latest revision to Design-Expert, V6.04*, offers a design under its Response Surface tab called "Historical Data." This design (or should we call it an "undesign"?) helps you set up a template for importing existing data. Simply identify how many numerical and/or categorical factors you wish to study and enter their names, units and extreme levels (minimum and maximum). Be careful when inputting categorical levels - their names must be consistently spelled, including upper and lower case letters. You also must enter the number of rows you will be importing (maximum is 32,766). Then enter the number, name and units of your response(s). Finally, enter the input (factor) and output (response) data that's been collected, or better yet, copy it from a Window's spreadsheet program such as Excel and paste it into Design-Expert (DX). (Note: When pasting data into DX, you must highlight the identical number of columns and rows for your destination area as you've copied to the clipboard from Excel or the like.) Now you're ready to do the analysis and take advantage of the powerful modeling, graphing and optimization features provided by Design-Expert software.
*If you own a permanently licensed copy of Design-Expert version 6 go to http://www.statease.com/soft_ftp.html#dx6updt for a patch that will update your software (individual or networked) with the latest enhancements. If you do not currently use Stat-Ease software, download a fully-functional free trial of DX6 at http://www.statease.com/dx6descr.html, which you can use at no cost for 30 days.
(Learn more about developing good predictive models by attending the 3-day computer-intensive workshop "Response Surface Methods for Process Optimization." For a description and course outline, go to http://www.statease.com/clas_rsm.html. Seats are still available for the next presentation in Minneapolis on July 17, but you must act fast to sign up. Do this via our web site or by calling our workshop coordinator, Sherry Klick, at 612.378.9449.)
2 - Info Alert: Contributed article on a drag-racing DOE and an idea on doing DOE on fishing poles (from a reader)
From: Mark Rusco, Assistant Professor, Ferris State U., Michigan
"I just reviewed your list of ideas for sample DOE's.* What a nice little resource!! I was surprised (and pleased) to see my name at the end of the list for the Drag Race simulator. I guess that amounts to my 15 minutes of fame. If you want to use my writeup in the newsletter, feel free. I've attached a copy."
Thanks, Mark, for your contribution:
All you readers, go to http://www.statease.com/pubs/dragracing.pdf
and take a look at a fun idea for teaching DOE. (If this portable document format
(PDF) does not open properly, you may need Adobe's free Acrobat Reader (now
out in version 5), which you can download at http://www.adobe.com/products/acrobat/readstep2.html.)
The software Mark refers to in his writeup can be seen by going to http://www.bethsoft.com.
Move your mouse cursor to their games list and select the ones for racing. Warning:
you're likely to get a bit distracted by all the adventure stuff displayed at
More from Mark:
"I've also developed another idea for in-class fun. Actually, this one is fun because we get to go outdoors. It is basically a take-off of the catapult one, but uses fishing poles. I vary pole length, fishing line strength, and the weight of a plastic casting plug. Response is casting distance. This is a good introductory one because the factors are all physical things the student can touch/feel. Plus, it's fun to walk into class carrying a couple of fishing poles and watch the students' faces."
Sounds like fun. I plan on trying this myself. I wonder how long it would take to replicate such a DOE on every lake in Minnesota (blocked, of course, to remove them as a source of variation).
*Go to http://www.statease.com/pubs/doe-self.pdf to view or download this collection of fun science projects that you can do at home with your children or in class with your students. You don't need any unusual equipment. The details are sketchy but they should be sufficient for creative experimenters. Use your imagination! If you have your own favorite DOE that anyone can do, send me the details. I'll add it to the list.
3 - Events Alert: A heads-up on DOE talks and demos
Click http://www.statease.com/events.html for a listing of where Stat-Ease consultants will be giving talks and doing DOE demos. We hope to see you sometime in the near future!
4 - Workshop Alert: Coming soon to Seattle
The "Experiment Design Made
Easy" workshop will be presented in Seattle on July 10th. See http://www.statease.com/clasedme.html
for a class description and link to sign up via our e-commerce site. Seats are still available but you must act fast. We will return to the Emerald City on Sept. 13 for the one-day "DOE Simplified." Take a virtual tour of the city at http://www.cityofseattle.net/html/visitor/tourism.htm.
For schedule and site information on all other Stat-Ease workshops see http://www.statease.com/clas_pub.html. To enroll, call us at 1.612.378.9449 or go to http://www.statease.com/prodwork.html. 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 Sherry Klick, Stat-Ease Workshop Coordinator, to get a quote.
5 - Believe it or not: A ballpark-sized DOE?
I visited Milwaukee recently and
while driving by their new baseball* stadium (an amazing building!) I listened
to a radio broadcast of a game in progress. The announcer, Bob Uecker (http://www.heybob.com/Spotlight_Bob%20Uecker.htm),
is renowned for his goofy commentary and he did not disappoint me on this occasion.
It turns out that the Brewer's stadium (see http://www.ballparks.com/baseball/national/miller.htm)
can be set up in different ways:
A. Windows: up or down
B. Roof: open or closed
Uecker laboriously went through all the statistics for wins/losses, batting averages, ad infinitum for all games played under the four stadium combinations. The stadium just opened this year so this data was based on a ridiculously low sample size of games. Do you suppose there may be some variability in the results? With weather to contend with, this would make an interesting problem for doing a DOE.
*Recommended reading for baseball
aficionados with a statistical bent: "Keep Your Eye On the Ball: Curve
Balls, Knuckleballs, and Fallacies of Baseball" by Robert G. Watts (mechanical
engineering, Tulane U.) and A. Terry Bahill, (systems engineering, U of Arizona-Tucson).
This book, and others like it from the same authors, can be found at Amazon's
I hope you learned something from this issue. Address your questions and comments to me at:
PS. Statistics quote for the month:
"When you come to a fork in
the road, take it."
- Yogi Berra.
Trademarks: Design-Ease, Design-Expert
and Stat-Ease are
registered trade-marks of Stat-Ease, Inc.
Acknowledgements to contributors:
- Students of Stat-Ease training and users of Stat-Ease software
- Stat-Ease consultants Pat Whitcomb (Principal) and Shari Kraber
(see http://www.statease.com/consult.html for resumes)
- Statistical advisor to Stat-Ease: Dr. Gary Oehlert
- Stat-Ease programmers, especially Tryg Helseth (Principal)
- Heidi Hansel, Stat-Ease communications specialist, and all the
remaining customer-service staff
Mark J. Anderson, PE, CQE
Principal, Stat-Ease, Inc. (http://www.statease.com)
Minneapolis, Minnesota USA