Bill's Story
DOE and Hewlett Packard

Was she wasting her time with her poorly planned experiment?

I first encountered DOE at Hewlett Packard. After receiving my chemistry degree, HP was my first employer. My supervisor asked me to help an ink-jet ink-manufacturing chemist with an experiment. She didn't have the equipment needed to make certain measurements. I was to prepare inks to her specification and make the measurements for her.

I was excited about this project and eager to get started. And, then I saw her experiments! She was varying all the ink ingredients at once! How could she possibly expect to make any sense of her data? Every scientist knows that you vary only one ingredient at a time so you can understand which one is having an effect. I felt that she was wasting her time and mine with her poorly planned experiments. I couldn't’t let this happen. I spoke with my mentor, an excellent chemist. I asked him how to avoid wasting our time and how to do the experiments correctly. I explained the situation: My colleague was varying all the ingredients at the same time. I arrogantly stated that this was the “worst set of experiments” I had ever seen! Was I ever wrong!

A New Way of Thinking was About to Change My Life!

She knew much more than I did!

My mentor told me that, although he didn't’t understand how it worked, he knew that there was a powerful technique called DOE that actually varied all the factors in an experiment at the same time. He suggested that I perform the experiments for my colleague exactly as specified. He also directed me to ask her about DOE.
Ah, the humility! I called my colleague and questioned her about DOE. She explained that DOE stands for Design of Experiments and that HP offered an internal class that I could attend. I signed up immediately.

In the class I learned how to use published tables of experiment designs to vary all the factors at the same time in a logical way to gain the maximum amount of experimental information with the smallest number of actual experiments.

I also learned about interactions!

Interactions are extremely common in nature, but I had left college with the mistaken impression that it was best to look at factors one at a time — ignoring the fact that they often interact.

[Baking is a simple, yet great example of interactions. When you bake, the time and the temperature interact. If you increase the temperature, you must decrease the time. The factors of temperature and time interact — they work together.]

I also learned to calculate the effect that each factor and interaction had on the measured property. I had the basics. I was ready to apply them to my work.

Back in the lab, I tackled ink with DOE. I was able to perform a small number of experiments and learn about interactions among the ingredients. I could see which ingredients appeared to be the most important, which ingredients interacted, and which ingredients were most important.

I’d learned a lot. However, my real goal was to know how to combine the ingredients to make the best ink. It seemed like I had the information I needed, but I couldn't’t see how to use that information to full advantage.

As I continued to use my new Design of Experiments skills my dissatisfaction increased. I needed to make better use of the information I was collecting…

A Critical Key Seemed to be Missing!

The ink was so successful that Hewlett Packard gave me stock options!

One day, several months later, good fortune struck. I received a postcard with a beautiful photograph of Mount Rainier on it. I was interested to see who had sent me such a pretty picture, so I turned the card over. It was from a company called Edgework and they were offering a class in Design Of Experiments and something called "Response Surface Methodology." Normally I would have hung the picture on my wall and ignored the ad, but in the upper left-hand corner of the card was a little picture. The picture showed a plot of Hours vs. Temperature for some unknown process. But the plot had contour lines on it – lines of equal product performance. This was what I had been hoping for! It looked like I could predict the combination of factors that would give me the best product. I called the number on the card and talked with Dave Doehlert. He assured me that he could teach me to predict the best product – what he called the "Sweet Spot." I registered for the class.
I arrived for class a few minutes before eight on Tuesday morning ready to learn. I glanced through the course manual and was relieved. I saw that we were going to learn about averages and standard deviations. I already knew about these and thought the review would be a nice way to get started.

I was surprised to find out how little I knew about averages and standard deviations! Dave taught us not only how to calculate them, but also what they are. He showed us how to calculate them by hand so that we would understand them better. He showed us the short-cut formula often used to calculate standard deviation and showed us how it could give the wrong answer. I had always thought the short-cut formula was the definition of standard deviation! Fortunately, Dave set me straight. He also showed us that many calculators can give the wrong answer, and showed us how to test our calculators to see if they could calculate standard deviations reliably. Wow! All this learning and we hadn't even begun what I had come for.

The rest of the class was equally eye opening. Dave explained everything in plain English. I didn't’t have to learn a new vocabulary – I could concentrate on learning the method. I could not believe how easy it was to determine the best combination of factors to get the best product. I had never seen anything like this in college.

When I returned to work I put the method to work right away. Hewlett Packard had introduced the Paintjet printer a few months earlier and its performance on overhead transparencies was poor. The colors were so washed out that they could not be easily read even in a dimly lit room. Many people had tried to fix this problem with no success. HP wanted this problem solved, but it seemed unsolvable. My boss asked me to try the new method on this problem. I did – and I found the answer very quickly. The resulting inks were so successful that HP awarded me stock options for my work.

This success alone would have made my time in class worthwhile, but I continued to have success with the method in different jobs. I used it to optimize plating processes, perform chemical interference studies, optimize chemical analyses, and optimize chemical stripping operations to name a few. I later attended a more advanced course, Experiment Strategies for Mixtures, also taught by Dave Doehlert.

I Had Entered A Better World

Enter A Better World!

You can learn what what I did -- and you can learn more!
You can learn to perform objective experiments and predict the Sweet Spot. And you can learn experiment design in plain English.

"But Bill," you may say, "I hate math. I hate it so much that I would rather stay in this world than have to do math."

You're not alone. The article, "Is Mathematics Necessary?" by Underwood Dudley, published in the November 1997 issue of The College Journal of Mathematics, claims that 50-70% of engineers and scientists seldom or never use math beyond elementary algebra and trigonometry.

So how can you reconcile not liking math with wanting to benefit from its use? You can let us help you. We teach you how to benefit from math without having to do math. We teach you to use software to perform the tedious and complicated calculations. We avoid theory and focus on practical applications. We use pictures instead of equations to teach you the important concepts.

Click Here to Find Out More