Stat-Ease Blog

Next in our 40th anniversary “Ask an Expert” blog series is John "Jay" Davies, who's an absolute rock star when it comes to teaching and implementing DOE. He's lent us his expertise before - see this talk from our 2022 Online DOE Summit - and he shared an anecdote with our statistical experts about how he approaches switching to DOE methods when working with new groups in the Army. He kindly agreed to let us publish it as part of this series.

For the past 14 years, I’ve been a Research Physicist with the U.S. Army DEVCOM Chemical Biological Center at Aberdeen Proving Grounds, MD as a member of the Decontamination Sciences Branch, which specializes in developing techniques/chemistries to neutralize chemical warfare agents. I’m dedicated to applied statistical analysis ranging from multi-laboratory precision studies to design of experiments (DOE). The Decontamination Sciences Branch has been integrating DOE methods into many of their chemical agent decontamination research programs.

I’m happy to report that the DOE methods here at the Chemical Biological Center are really catching on. I collaborated on 24 DOEs from 2014 through 2021. Then, in 2021-22, we completed 26 DOEs across 10 different programs. I’ve been doing a lot of mixture-process DOEs with the Bio Sciences groups for synthetic biology and bio manufacturing applications, and once the other groups saw the information that we were getting from just a single day’s worth of data, they too wanted to try DOE.

Lately, I’ve changed the formula that I use for the initial consultations when visiting a group that has expressed an interest in DOE but has never used DOE before. Previously we’d go right into their project, and I’d tell them how we might construct a DOE for their application. However, I’ve found that it’s too much of a culture shock if we go right into talking about what a DOE for their application might look like. Instead, especially if I’m working with a group that has no DOE experience at all, I now devote about 1 hour to discuss DOE methods in general before we even mention their actual application. In this discussion, I reveal the major differences that they are going to see with a DOE, which are:

• We’re not going to replicate every sample, we may even have zero exact replication.
• We’re not going to test every possible combination of factors.
• Sample sizes are going to be 70% to 95% smaller than what they are used to doing.
• We are not going to change “one factor at a time”, in fact we’ll be changing all factors at once.
• The designs might look chaotic, but they are strategically created to contain a hidden orthogonal structure, along with hidden replication, that is not apparent.
• You will see that many of the DOE samples contain factor combinations that don’t seem to make sense. This is because each sample is not designed as a stand-alone shot at optimization. Rather, the samples cumulatively are working in concert to tease out the influences of each factor. This will let us fit a predictive model that we will then use to predict the optimal settings of factors.

Recently, I was following this format with a group that had never used DOE before. We had a great back-and-forth dialog as I went through the bullets above and explained a bit about each point. They asked many questions and were really following along. Then, after about an hour we got into their application and I just sketched out a prototype quadratic mixture-process DOE that I thought would give them a good idea of what the initial DOE might look like, with 30 samples in total. I then went over what some simulated outputs for the DOE generated prediction model might look like. At this point one of them stopped me and with a very perplexed look on his face, said “hold on, hold on…wait a minute here. Are you telling us that if we run just those 30 samples, we would be able to predict the optimal formulation and the optimal process setting for this system?“

This scientist had been following along, asking questions and really absorbing the information in the past hour as we walked through the DOE basics, but I could see that at that moment things were just sinking in. He realized the ramifications of what we had just discussed – typically, this group might have had to run several hundreds of samples to characterize similar systems, but with DOE they would only need about 30 samples. I responded to his question saying, “Yes that’s exactly what I’m telling you. We’ve run dozens of these mixture-process DOEs, many of them much more complex than this system, and they do work.” This individual, a mid-career researcher, then responded, “How is it possible that we have not heard of this stuff before?” I told him, “I can’t give you a good answer to that one.”

And there you have it! Let us know if you want to talk about saving time & money with DOE: our statistical experts and first-in-class software make it easier than ever.

DISTRIBUTION STATEMENT A. Approved for Public Release: Distribution is Unlimited

Stat-Ease is collaborating with Dr. Pelton to help users who achieve experimental success better communicate their results. Enjoy this article on improving how you say what you say!

In Act 1, Scene 1 of Shakespeare’s tragedy King Lear, Lear asks his three daughters to proclaim their affection for him which the first two, Goneril and Regan, do with genuine warmth, but the third, Cordelia, does not. She rather coldly says that she loves her Majesty according only to her bond, no more nor less. He’s taken somewhat aback by her callous comment and responds by saying “How, how Cordelia! Mend your speech a little, lest it mar your fortunes.”

Shakespearean actors worth their salt know full well that it’s not only the meaning of the words they speak but the way they speak them that makes what they say worth listening to. They are keenly aware of how to use articulation, modulation, tempo, sound and pronunciation to affect their speech. They are elocutionists who, to paraphrase one dictionary’s definition, are masters in the art of speaking effectively in public.

Here are three key steps to improving—or mending—your speech so you, too, can speak more effectively. Once you’ve read them and practiced the suggested exercises, you’ll be well on your way to becoming a more polished speaker and, who knows, even a proficient enough master to go on stage and play Goneril, Regan, Cordelia or Lear.

First: Variety above all else. You never want your voice to sound colorless, dull, passive or lifeless, so to give it character and make it interesting to listen to, change speeds, expand its range and play with dynamics. Which would you rather see, a river placidly and monotonously rolling along without anything in it to grab and hold your interest or one that’s alive with activities that catch your eye and make you want to stop and pay attention? The same with the voice and variety.

Also, pause, pause and pause yet again. You never want to run phrases together so that you prevent audiences from understanding, appreciating or enjoying what you’re saying. Silence is, indeed, golden so, to quote the great American raconteur Will Rogers, “never miss a good chance to shut up.” Actors and storytellers vary their voices and use silence to keep their audiences engaged and involved. Listen to your favorite actor or actress reciting a poem or reading a novel and you’ll hear what I mean. You’ll certainly be taken in by how they use their voices and pauses to hold your interest. Better yet, record yourself reading, say, A. E. Houseman’s short poem “When I was one and twenty” from “A Shropshire Lad” and listen to what you sound like when you play it back. Did you vary speed, range and dynamics and use pauses to make the poem come alive and be worth listening to, or did you merely go through the motions and read it without vocal inflection or pausing so it came across as boring, bland and, in a word, blah. Hopefully, the former.

When I was one-and-twenty

I heard a wise man say,

‘Give crowns and pounds and guineas

But not your heart away;

Give pearls away and rubies

But keep you fancy free.’

But I was one-and-twenty,

No use to talk to me.

When I was one-and-twenty

I heard him say again,

‘The heart out of the bosom

Was never given in vain;

‘Tis paid with sighs a plenty

And sold for endless rue.’

And I am two-and-twenty,

And oh, ‘tis true, ‘tis true.

You’ll find that, as you practice varying your voice and pausing, you, too, will turn into an actor or storyteller who’s more than adept at using variety and silence to persuade, influence, motivate, entertain or educate the people you’re talking to. So, vary away and shush.

Second: Enunciate, enunciate, enunciate. English is a hard, percussive language and, to speak it well, consonants need to be sharp and incisive. Many speakers of English, both native and foreign, don’t do this enough and, as a result, listeners all too often fail to understand what’s being said because speakers don’t pronounce their “b”s, “t”s, “v”s, “l”s, “m”s, “p”s or “d”s clearly, cleanly and consistently. So ask yourself which consonants you don’t articulate well and work on them. Try the following tongue twisters and see if they’ll help. As you go through them, notice how many consonants you miss—quite a few, I’ll wager.

• Tom took Tony to Tennessee to teach two turtles to tickle a tree
• Bring back Bill’s bright blue baseball bat
• Sally saw Sylvester stacking silver saucers side by side
• Wes waited patiently while Willie wound Walt’s weighty watch
• Dandy Doug Doolittle danced the night away with delightfully dreamy Debbie Dalrymple
• Peter Piper picked a peck of pickled peppers
• Unique New York, unique New York, unique New York

Try them again making sure to enunciate the next consonant as emphatically as the one before and you’ll notice a marked improvement.

So, enunciate sharply and consistently and you’ll be better off for it.

Third: Handle with care. For your voice to be the expressive, compelling, engaging and appealing instrument you want it to be, it needs more than its fair share of TLC.

It is extremely fragile, though paradoxically quite strong, and can become damaged much more easily than people think it can without proper care. So, to speak well:

• Rest it often by taking frequent vocal “naps”—your voice consists of two muscles or folds (not cords as some people call them) that need to be rested to work at peak efficiency, so from time to time pause to let them relax and return to their normal position of repose.
• Keep it moist by drinking water that’s warm or at room temperature but never cold—if you drink bottled water that’s been in the fridge or with ice, it will anesthetize your vocal folds and make them less flexible and pliable. Remember, too, that they, like gears, need to be constantly lubricated so that they don’t dry out and become rough, scratchy and irritated—conditions that, if left unchecked, can lead to damage, in some cases serious damage. By the way, if you become unsettled or uncomfortable because your mouth has suddenly gone dry and you have no water handy to wet it simply bite your tongue or the inside of your cheek and moisture will return.
• Keep it warm. Muscles that are kept cold become rigid, taut, inflexible and unpliable and, therefore, prone to injury. So, if the room you’re speaking in is cool or if the air conditioning is too high and you can’t turn it down, make sure to wear a turtle neck sweater or some other bit of clothing around your neck to keep your folds from tightening up. Of course, by drinking warm (or room temperature) water, you’ll also help keep your voice warm and in good shape.

Also, avoid as much as possible:

• Smoking—this is the most major of major irritants and will do irreparable harm to the voice and should be avoided at all costs.
• Drinking tea or coffee—these are irritants that dehydrate the voice and keep the folds from working properly. (Shying away from sucking lemons or other acidic fruit that will do the same thing is also a good idea.)
• Drinking milk or eating chocolate—these will coat the voice and make it harder for the folds to work properly
• Shouting or trying to speak above noise—this is an irritant that will seriously harm the voice and can cause considerable damage if done for too long at a time.
• Coughing or clearing the throat—these irritants will also cause damage and, even, considerable damage if done too often or for too long at a time
• Whispering—curiously, this is also an irritant that can do considerable damage if done for too long
• Speaking consistently at one pitch level—this will tire the voice, irritate it and make it less responsive if done for too long at a time.

To paraphrase W. H. Auden, “all (you) have is a voice,” so the more you take care of it and use it wisely, the more it will be able to do what you ask it to.

The British actress Dame Penelope Keith once said that when she went to school everyone had elocution lessons, not to sound posh but so they could be understood. Understanding, of course, is at the heart of any communication so it goes without saying that the more effectively and expertly you use variety, silence and diction to speak and the more you take care of what the composer Richard Strauss calls “the most beautiful instrument in the world (and the most difficult to play)”, the greater the impact of what you say will have on those listening to you. In short, just remember that what you say will only be as good as how you say it.

Dr. David Pelton has been a professional communicator for over 45 years and has taught courses in communication and communication-related subjects for a number of national and international training/development organizations including PetroSkills, Energy Delta Institute (The Netherlands), The Learning Tree (Malaysia), Integrative Learning & Consulting, Ltd. (Singapore), and the Oxford Management Centre (UK/UAE). He is currently President of Pelton Communications, LLC and holds degrees from Cornell University, The New England Conservatory of Music, and the University of Cincinnati. He has performed for, and spoken to, audiences in the United States, Central and Western Europe, Armenia, Azerbaijan, Russia, The Ukraine, Africa, The Middle East, and Southeast Asia. He has also taught at major US colleges and universities and has done voice over work and been an active seminar/workshop trainer/facilitator for businesses and organizations in California, Colorado, Illinois, Louisiana, Massachusetts, New York, Rhode Island, Texas, Virginia and in Angola, Canada, Australia, England, Germany, Holland, Ireland, Kazakhstan, Wales, the Czech and Slovak Republics, Benin, and Nigeria. Today he is a member of numerous training institutes and societies and enjoys a national and international reputation as a communications consultant, lecturer, trainer, and coach. He can be reached at peltoncommunications@gmail.com.