Monday, October 12. 2009
Recently, JMP has been deluged with requests for information about Design of Experiments (DOE or DOX). Was it due to atmospheric disruption when NASA hit the lunar south pole last week? Or shall we just chalk it up to a growing desire to work smart and make better use of resources in the workplace?
Never fear, JMP is responding. On October 28, author and Arizona State University professor Douglas Montgomery and JMP’s Brad Jones are offering a free seminar on DOE in Phoenix. At the seminar we will give away some copies of several books, including Montgomery’s latest edition of Design and Analysis of Experiments and a new SAS Press book by W.L. Gore employees and JMP users José and Brenda Ramírez, Analyzing and Interpreting Continuous Data Using JMP: A Step-by-Step Guide.
Join Doug, Brad, Susan Glick, John Guerrero and the southwest US JMP team on Thursday, October 28. Seats are filling fast so register today.
We also just added a December 3 live DOE Webcast hosted by JMP’s Tom Donnelly. It is part of our Master Your JMP Skills series. Sit back at your desk, put your feet up and join this DOE event. Registration is required.
Monday, September 21. 2009
It is a rare and exhilarating opportunity to dine with a legend. And at Discovery 2009, that is exactly what attendees did.
After a full day of keynote speakers, breakout sessions, poster browsing and meeting the developers, conference-goers convened for deep-dish pizza and the chance to hear from Dr. George E.P. Box, who many would label “the father of modern-day statistics.”
The audience was filled with people who learned statistics from his many books, including “Statistics for Experimenters.” Each person received a copy and the chance to have it signed by the man for which Box-Cox transformations, Box-Jenkins models and Box-Behnken designs are named.
In the words of one audience member, his “book is one of the best. I look at it every week when helping people set up experiments.”
Dr. Bradley Jones, Director of R&D at JMP, opened the event, calling Box a “personal hero” and “the leading statistician of the previous millennium.”
Box entered to electrifying applause and a standing ovation from his many admirers. Clearly overwhelmed by the moving response, he jokingly likened the moment to a story he remembered of a sultan who, on his 21st birthday, attended a celebration in his honor where there were many concubines and “he didn’t know where to start!”
Infusing his entire presentation with humor and fascinating tales of his memories, Box focused on sequential design of experiments. He attributed much of what he knows about DOE to Ronald A. Fisher. Box explained that Fisher couldn’t find the things he was looking for in his data, “and he was right. Even if he had had the fastest available computer, he’d still be right,” said Box. Therefore, Fisher figured out how to study a number of factors at one time. And so, the beginnings of DOE.
Having worked and studied with many other famous statisticians and analytic thinkers, Box did not hesitate to share his characterizations of them. He told a story about Dr. Bill Hunter and how he required his students to run an experiment. Apparently a variety of subjects was studied, from baking cakes to experimenting with sex to finding a better way to get out of a spin in an airplane (according to Box, the student didn’t actually kill himself, although he came close).
At the conclusion of his presentation, audience members were invited to participate in a Q&A session. Dr. Dick De Veaux, professor of mathematics and statistics at Williams College and a Discovery Keynote Speaker, had a funny exchange with Box. It went like this:
De Veaux: “You invented a lot of things, and we are thankful for all of those. But the box plot, you didn’t invent. And you once confided in me you’d like to invent your own plot. I would like to know how that’s going.”
Box (chuckling): “Well, John Tukey was working in the same group as me at the time that he invented the box plot. And he decided to call it that. Why? I have no idea. He was a remarkable man. But on the other hand, I sometimes got irritated with him. I remember once, I had been asked to give a seminar. And he thought he knew what I would say and continued to interrupt me, but he didn’t know what I was going to say. I decided to take a vote, if it comes out in my favor, John Tukey will keep quiet. And it did come out in my favor.”
De Veaux: “So there!”
Box: “But he really was a remarkable person in most ways.”
His answer to the why DOE has not taken root in more organizations where Six Sigma and quality process control already occur was priceless as well. He said, “I don’t see why people doing Six Sigma shouldn’t do DOE. I’d say, if they aren’t, you should teach them and say it’s Six Sigma.”
Breakout session presenter and experimental design advocate Dr. Chris Nachtsheim asked Box if he had any comments on the state of the statistical profession today. Box explained that in order to teach statistics today, all you need is a math degree. He said that many professors “aren’t statisticians at all; they are actually mathematicians who didn’t quite make it.” Therefore, it is very unlikely that these mathematicians have ever run an experiment.
According to Box, the difficulty of getting DOE to take root lies in the fact that these mathematicians “can’t really get the fact that it’s not about proving a theorem, it’s about being curious about things. There aren’t enough people who will apply [DOE] as a way of finding things out. But maybe with JMP, things will change that way.”
Well said, Dr. Box. Thank you for sharing your time, talents and thoughts with us.
Friday, August 21. 2009
In The Wall Street Journal, Michael Schrage and MIT colleague Erik Brynjolfsson describe how technology now enables all employees -- not just R&D scientists or market researchers - to test new ideas faster and cheaper than ever before.
The key? Faster experimentation for hypothesis testing. The promise? Innovation at warp speed.
Erik suggests two requirements for innovation -- a creative flash and a quantitative mindset that translates the flash into measurable and testable experiments.
Michael suggests that new electronic technologies for capturing and examining results almost immediately from small, targeted experiments lay the groundwork for innovation for companies (like Google) that are bold enough to breed a culture of experimentation.
Want to learn more? Meet and speak with Michael Schrage at the JMP Innovators' Summit in Chicago on Friday and Saturday, September 18 and 19. Michael is there both days -- opening the sessions each day, hosting a group of attendees at Friday’s dinner and moderating the closing panel session on Saturday.
Consider coming a few days early to attend the Discovery 2009 conference and learn about how people use JMP, including for measurable, testable experiments. The creative flash? Well, that’s up to you.
Register now for one or both events.
Tuesday, February 24. 2009
The first in the Government Communities in Collaboration Breakfast series is tomorrow at the National Press Club in Washington, D.C.
The series is designed specifically for leaders in federal government agencies to learn how to:
- Increase efficiency with smaller budgets.
- Exceed objectives under increased resource constraints through process improvement.
- Save time and resources through enriched use of the acquisition life cycle.
The key business topic for February is design of experiments.
Attendees will learn about the use of several new types of DOE methods on both real and simulation experimental data. The presentation will be based on unclassified briefs by the speaker at recent Military Operations Research Society Symposiums. The featured solutions will illustrate the benefits of using a sequential approach to ensure that the desired answer is achieved in a minimum number of trials.
The topic for the government leaders breakfast meeting in March will be data modeling and data visualization to understand complex programs. The meeting is scheduled for March 24, during SAS Global Forum. Look for more info here and elsewhere on the JMP Web site on that upcoming event.
Thursday, May 29. 2008
Brad Jones, JMP's Director of Statistical R&D, has been elected a Fellow of the American Statistical Association, the most prominent professional statistical society in the US. This honor recognizes "outstanding professional contributions to and leadership in the field of statistical science."
Brad has a career-long passion for the field of optimal experimental design. Experiments are the way you learn, by trial and error, how to make things work better, and optimal designed experiments are simply the way you learn the most from a given number of experimental trials. The world is too complicated to discover things by pure theory – we need some experimental data to find out how the world works.
For about 25 years, Brad has been working on a Big Idea that focuses most of his work. The Big Idea is that experimental design has to fit naturally within the workflow of an engineer, and the best way to make that happen is for great software to support that workflow. For new cutting-edge software to evolve, statisticians had to change the way they think about experimental design.
In the past, statisticians created designs by algebraic and geometric patterns; the resulting designs could accommodate only certain situations with fixed numbers of runs and factors. For example, if you had a budget for 17 runs on five categorical factors, you had to throw one run away to get a classical design. In the classical design world, there was a lot to learn, and that learning burden was an impediment to engineers.
Brad's Big Idea for the engineering workflow turned experimental design upside down. Instead of forcing conditions to fit a tabled design, you tell the computer software what your experiment is all about and how many runs you can afford, and the computer software creates a custom-built design for that situation – a design that is optimal for learning what you need to know from the experiment.
Brad adopted the field of optimal experimental design, and, with other statisticians in the field, pushed all the boundaries to make it a rich and robust field. One early breakthrough, by Chris Nachtsheim and Ruth Meyer, was a general algorithm to optimize the design, called coordinate exchange. Brad adopted and refined the coordinate exchange algorithm. Another significant development was Brad's work with co-author Bill DuMouchel on Bayesian D-Optimal designs. These designs try to estimate as many potential interaction effects as possible, even when they are not all estimable.
Then Brad recognized that the Bayesian D-Optimal method could be applied even to main effects, and he pioneered the optimal design for what are called supersaturated designs, which allow there to be more factors than runs. This occurs in screening situations where you expect only a few factors to be large, and the objective is to identify these large factors. In collaboration with Chris Gotwalt at SAS and other statisticians, Brad went on to pioneer I-Optimal designs, various space-filling designs, mixture designs, split plot designs, designs for nonlinear models, spherical designs, choice designs for market research and designs for computer experiments.
For the Big Idea to work – to get engineers used to designing experiments – there also had to be fitting and analysis tools. Here Brad invented a way to visualize a response surface by taking vertical cross sections across each factor, given fixed values of other factors. This tool, called the Profiler, is now implemented in just about every DOE fitting system. When Brad joined SAS to work with JMP, the Profiler was extended to provide complete optimization services and recently includes optimization in the presence of variability (stochastic optimization).
For the Big Idea to gain traction, Brad had to evangelize. To that end, he has established ties with many leading DOE researchers and has jointly authored papers with some of them. Brad is a regular speaker at academic statistics seminars, JMP seminars and academic meetings. One recent meeting was the International Conference on Design of Industrial Experiments at the University of Antwerp, where Brad presented the public defense of his PhD dissertation.
In the last two years, Brad has submitted numerous papers for publications, most of them with co-authors. For seminars, Brad and I developed a popular demonstration we call the "card trick" – which involves doing a live supersaturated screening experiment with the audience.
On the side, Brad is a concert violinist, a highly ranked Go player and author, has bred show dogs that compete nationally, and is a marathon runner. He was a published author in the field of photochemistry at age 17.
I am delighted to see Brad recognized as an ASA Fellow.
Monday, May 5. 2008
Randomizing an experiment completely is often either impossible or prohibitively expensive. That's where split-plot designs can be valuable. Split-plot designs allow you to fix certain factors for several runs in a row. Within each block of runs (or whole plot), the factors that are hard to change remain fixed while the others vary at random from run to run. This makes the logistics of running a design simpler.
If you’ve had the opportunity to see JMP R&D Director Bradley Jones demonstrate how JMP Custom Designer handles split-plot designs elegantly and efficiently, you will want to read the paper he recently co-authored.
In the May 2007 issue of Journal of the Royal Statistical Society: Series C (Applied Statistics), Brad and Professor Peter Goos from Universiteit Antwerpen introduce a new method for generating optimal split-plot designs. In the paper, they demonstrate the usefulness of this flexibility with a 100-run polypropylene experiment involving 11 factors. In the experiment, they found a design that is substantially more efficient than designs produced using other approaches.
We also have more resources on design of experiments (DOE or DOX).
If you have JMP, check out sample data and instructions for generating a split-plot design.
Thursday, April 10. 2008
The ASQ World Conference on Quality and Improvement, May 5-7 in Houston, is the perfect place to discuss design of experiments (DOE), Visual Six Sigma and Voice of the Customer research. JMP staff will be joining those conversations throughout the conference.
If you’re going, come visit our Seeing Is Believing Demo Theater in Booth 101. We have scheduled these 20-minute demos:
• Visual Six Sigma for Manufacturing, May 5, 10:05 a.m.
• Listen to the Voice of the Customer, May 5, 2:35 p.m.
• Visual Six Sigma for Transactional Data, May 6, 10:05 a.m.
• Custom-Fit Your Designed Experiments, May 6, 2:50 p.m.
If you’ll still be in Houston on May 19, sign up to take our free seminar, with lunch included, on design of experiments. The seminar, Practical Design of Experiments and Visual Analytics will focus on the chemical, service, oil and gas industries. One of our DOE experts (and baseball data guru) Lou Valente will talk about how designed experiments can help you figure out which adjustments will yield the greatest gains in quality or process improvement – saving you time and money.
Monday, March 31. 2008
 The inspiration for our latest data story – on using JMP for fantasy baseball – came from Lou Valente, one of our product managers and an ardent New York Yankees fan. Lou is a synthetic organic chemist, a Six Sigma Black Belt and a passionate practitioner of design of experiments. He was a worldwide quality manager at Kodak in the Synthetic Chemicals Division before joining JMP about a year ago.
But he’s no stranger to JMP. Lou has been using JMP for work and fantasy baseball for nearly 20 years. He has won the championship eight times in his fantasy league in the past 19 seasons. His team, the Vintage Yanks, also has the most consistent performance in his league, as the JMP graph above shows. For the past seven years, his mean win percentage is nearly 70 percent, while most other teams’ figures are in the 40-50 percent range.
Lou’s data file and analysis of the top 200 professional baseball players is the basis of the baseball data story. The file is available for download from the JMP File Exchange.
I chatted with Lou about the history of his interest in fantasy baseball.
Me: How did you get started playing fantasy baseball?
Lou: It began with board games, dice and probability. But it all had to do with my passion for baseball. My passion for statistics came from baseball.
I grew up in New York in the 1960s, only 15 minutes from Yankee Stadium. I was very influenced by Mickey Mantle and Roger Maris. And my dad was in the minor league farm system for the Yankees. So we were a big baseball family.
I taught my brother when he was 5 years old how to do batting averages. I showed him how 1 for 10 and 2 for 20 were the same thing. The calculation for earned run averages had to be normalized for nine innings, and this seemed like magic to him. Baseball definitely played a part in making us math-literate, and it made it fun.
A board game came out in the ’60s called “Challenge the Yankees.” It was only out for two years. It was a game that had all of the All-Stars from all teams versus the Yankees since at that time it required a team of All-Stars to compete with them.
Me: What was the game like?
Lou: That game introduced me to statistics and probability. Every card and every player had the numbers 2 to 12 on it, and by throwing dice, depending on what entries were on the card – single, home run, fly out, ground out – the game could approximate a player’s statistics using the probabilities of dice.
My cousin used to come from Michigan every summer. He was in college at the time, and I was 10 years old. He showed me how each dice roll had a different probability. You could get a 2 only with snake eyes, whereas you could have a 3 with a 1 and a 2, or a 2 and a 1. Six, 7 and 8 were the most frequent rolls. So the person who invented “Challenge the Yankees” realized that it approximates the statistics of baseball through the use of the dice.
Then the game disappeared ’cause if you didn’t live in New York, you probably didn’t buy it. On very rare occasions, you can find the original version on eBay for over $1,000.
Me: Then what did you do? You stopped playing?
Lou: No. Then Strat-O-Matic came along in the ’60s. That game is still played today, and there are conventions all over the United States for this baseball game. The guy who invented the game realized he could make “the game of games” by adding one more die.
There was one red die and two white dice. And the red die indicated the columns, so now you had six columns and 2 through 12 under each column. Three columns resided on the hitters card, and three columns resided on the pitchers card. The statistical granularity of all the things that could happen increased by six. This board game really took off, and everyone and his brother was playing it. And every year, people buy new cards with updated statistics from the most recently completed season.
Me: Then this led you to fantasy baseball?
Lou: Yes. Before computers, fantasy baseball was all on paper. Then it went with the age of computers and became more automated and easier. I’ve been playing fantasy baseball since 1988, and I’ve had eight championships in 19 years. I don’t win any money. The winner in my league gets a free subscription to the fantasy baseball Web site, which is worth only $20. A lot of people do play for money, and I probably should have been playing for money. But that’s not what it’s all about.
What it’s really about is baseball. As I got older, I sort of lost track of baseball because of college and graduate school. And I only knew the Yankee players. Fantasy baseball allows me to know every team and every player. It increased my awareness of the game of baseball again. Plus, it was fun to play against co-workers and gain bragging rights every year!
Monday, February 18. 2008
JMP staff members Susan Glick, Jami Hampton, John Guerrero and I attended the ASQ Lean Six Sigma event in Phoenix Arizona the week of Feb. 10. The JMP booth was buzzing with interested attendees looking to capitalize on JMP’s Lean Visual Six Sigma concepts.
Attendees were keenly excited about JMP’s Design of Experiments (DOE) capabilities, which enable organizations to execute unique designs with the DOE Custom Designer to improve their business performance and customer satisfaction.
We were fortunate to have Rob Reul, co-founder of Isometric Solutions, as a keynote speaker. Rob presented an outstanding discussion on deploying Voice of the Customer (VOC) analytics to drive business performance and enhance the process of Six Sigma project selection.
JMP really shined as Rob showed examples of several categorical and conjoint techniques unique to JMP, which are necessary to achieve world-class business results.
“Six Sigma techniques to improve manufacturing and service operations and Design for Six Sigma are well-established. Applying appropriate Six Sigma analytics for the VOC space is truly the next innovative approach that must be adopted in order to stay ahead of the competition,” Rob said.
The room was packed, and we ran out of business cards because Rob’s talk generated such a high level of interest.
If that was not exciting enough, Dr. Roselinde Kessels, postdoctoral researcher at North Carolina State University, presented a workshop showcasing the unparalleled features of JMP to perform conjoint studies. She wowed the audience with the easy-to-use, powerful features of JMP’s Custom Designer for performing efficient designs with graphical analysis techniques.
Friday, June 29. 2007
I just finished the draft of a new short course about design of experiments called Custom Designs for Experiments. SAS Education launched a high level training experience several years ago known as the Business Knowledge Series (BKS).
BKS was a opportunity for our users to spend time in a class with a reknown expert. This idea was later advanced in a new Analytical Lecture Series (ALS) comprised of half-day seminars in a Live Web format on special topics, again by experts in the field and in academia. (I was fortunate to be able to assist Dr. J. Stuart Hunter when he presented his seminar about time series analysis in the context of statistical process control. JMP was featured heavily in all of the demonstrations. Working with Dr. Hunter is always a pleasure. I never fail to learn more, even about a familiar topic, whenever we get together.)
After the success of the original ALS, SAS Education decided to expand the offerings. JMP training was invited to contribute a short course about custom design. It will premiere on August 9, 2007. You can read more about it at Custom Designs for Experiments, where there is a detailed outline.
This seminar introduces custom designs by illustrating how simple it is to design an experiment for any situation through a complex but realistic example.
Beyond this seminar, we also offer more in-depth training for custom design and the principles of experimentation in a wonderful two-day course, Modern Design of Experiments. Information about this course is available at Modern Design of Experiments, including a detailed course outline.
I hope to see you in a class soon!
Monday, June 25. 2007
It is hard to believe that the JMP User Conference is over for another year. So much happened in just one week! I left with lots of new ideas.
Some of these ideas occurred to me in the lunch time roundtable discussions. I was fortunate to moderate one about design of experiments (DOE) on both days of the conference. Our expert was Dr. Stuart Hunter. On the second day, we had a surprise guest join us: Dr. Doug Montgomery, the keynote speaker!
They were asked for their opinion about what the big new areas will be for DOE. Both experts agreed on three fronts: designs for computer experiments, non-linear models, and generalized linear models (GLM). They feel that theory is at hand to address these designs but to put it in to practice will take good software.
JMP offers non-linear design and space-filling designs and gaussian process models for computer experiments. JMP can also fit many GLM models. So it seems that the experts and JMP foresee the same future.
|
JMP Statistical Discovery Software from SAS
is proud to bring you this blog on all things related to
data visualization, visual Six Sigma, design of experiments
and other statistical topics.
