The W. Edwards Deming Institute Blog

Deming Regression

Most of Dr. Deming’s management work requires no understanding of advanced statistical methods. He was also a statistician and this post takes a look at one of his contributions to the field of statistics: the Deming Regression.

book cover image: Statistical Adjustment of Data by W. Edwards Deming

In his book, Statistical Adjustment of Data (1943), W. Edwards Deming discussed, among other things, various methods to find a line of best fit to a collection of data. One of those was a method to use when both variables were subject to measurement error (instead of just one variable being subject to measurement error).

The method became known as Deming Regression and is similar to the idea of finding a best fit line through data using the least squares method of simple linear regression. The Deming Regression is commonly used in clinical chemistry. The general concept was originally proposed by R. J. Adcock (in 1878) and refined by C. H. Kummell in 1879. It was largely overlooked until T. C. Koopmans (a Nobel Prize winning economist) published on the topic in 1937 and then W. Edwards Deming’s 1943 book.

This post isn’t going to be of interest to a fair number of readers (at least in as far as understanding the statistics goes) but I think it is an interesting view into the breadth of Deming’s work. It also shows once again both how Dr. Deming was able to use and popularize good work by those who came before him and how long good ideas can sit unused. That second point is one I feel is overlooked by many who seek the new new thing instead of just looking at all the very good old ideas that are not being used.

You may read more about the Deming Regression on the NCSS statistical software web site. Here is a plot from their article:

plot of data showing the Deming regression and normal least squares regression lines

Read the rest of this entry »


Exploring Complex Problems Using Systems Thinking

Cornell Policy Review published a special issue exploring the application of systems thinking to public policy problems. Graduate students were given an introduction to systems thinking and then applied the concepts to address issues their field.

Students applied systems thinking to a wide array of problems, and they reported finding DSRP [distinctions, systems, relationships, and perspectives] transformative for their work. We discuss implications for future research on the utility of relatively brief exposure to systems thinking rules for those who work on complex problems in and outside academia.

The students explored a wide variety of problems including:

Short articles and presentations are available online by each of the students showing their application of systems thinking to a problem in their public policy field.

This special issue of the Cornell Policy Review provides clear examples of how applying systems thinking to complex problems creates a framework to help understand the important issues involved. Often big problems are so complex we end up hoping that addressing individual components of the problem will end up improving the results we actually care about at a systems level. Unfortunately this process and hope are not the best strategy – the system results are not the sum of the individual parts but come from the interaction of those parts.

Read the rest of this entry »


The Real Lessons of the Red Bead Factory

The video shows a recorded webinar for the Healthcare Value Network by Mark Graban and Mike Stoecklein. In the video they explore the real lessons of Dr. Deming’s famous red bead factory demonstration and the principle of understanding and managing variation.

Mark mentions how Bill Boller, with Hewlett-Packard, created the red bead experiment as a present for Dr. Deming in 1982. Dr. Deming then used it on the first day of his 4 day seminars. And throughout the rest of the seminar he would refer back to the red bead game to emphasis points he wanted to make.

Mike:

He [Dr. Deming in seminars] would say it must be because of good management that we went from 64 to 62, so clearly we are on the right track. He was articulating what was going on in the minds of people with the prevailing style of management. And he called it the mythology of management – how we think because the the things we do it has a cause and effect on the what we see.

In the red bead experiment people could clearly see that the variation in the data were not due to causes that Dr. Deming mentioned. And in seeing that they can understand that just because you see variation in data that doesn’t mean you can identify causes – often there is no cause it is just variation (also see the Dangers of Forgetting the Proxy Nature of Data).

Mark showed how variation can mislead and referenced a simulation the BBC did and wrote about in: Can chance make you a killer?

Mike quotes Ed Baker (at Ford) on seeing that when effort was being made to apply the ideas that grow from an understanding of variation was only being applied on the factor floor:

Where it needs to be applied is understanding variation as it relates to the overall business strategy or company-wide systems.

In several previous posts on our blog we have discussed that topic, including: Don’t Limit Improvements to Low Level Process Improvement.

This video is another in the continually growing number of webcasts for those learning about Deming’s management ideas. Many of these are provided by The W. Edwards Deming Institute itself but there are also more, like this one, that are made available by others. And there are many that may not directly mention Deming but discuss aspects of related ideas, especially lean thinking. Those seeking to learn are lucky to have so many resources on Deming’s ideas readily available online.

Related: We are Here to Learn, to Make a Difference and to Have FunLessons From the Red Bead Experiment with Dr. DemingWe Need to Understand Variation to Manage Effectively


Joy in Learning

Deming Institute podcast icon

We have another Deming Institute podcast with David Langford, to share with you – Where is all the Joy? (download podcast).

David explains that when looking to improve the place to begin is to examine your circle of influence and determine where you have a chance to help move toward better practices. A clip from David’s presentation at a previous Deming Institute conference explores this idea: Change has to Start from the Top.

People are very shocked coming out of the school system when they go into pretty innovative companies and then they are expected to start thinking and creating and working together with other people to a very high level. And students are often shocked even coming out of major universities, they don’t know what that is.

I talked to a computer science professor once who said he would give very open ended projects to students and the very best students would just panic. They just continually come back with “how do you want it” “do you want it like this “do you want it like that” “or do you…” They were just very boss oriented. And if you fell into that and told them exactly what to do then they would get the straight A’s, they would do exactly what they were supposed to do. But you wouldn’t get any innovative ideas or new breakthroughs in thinking coming from that.

So we have to think, long and hard about what is the aim of the system.

Do we want to educate students to be able to think creatively and work together to find and implement solutions? And to evaluate how things are working and if necessary go learn more about certain aspects and then apply that learning to an attempt to improve? It sure seems like a good idea to me.

But, as David says, our education system largely focuses on individual test taking and paper writing. There are some efforts that focus on project based learning with a great deal of students learning to work together. But that is a very limited portion of the education system today.

Working to create a system that supports and embraces joy in learning in students is what David recommends. There is no recipe for how that is done. There are many ideas that can help you decide how to create a system that works to restore and build student’s innate joy in learning (and we have many previous posts on such ideas). But Deming doesn’t provide a recipe, he provides ideas that are useful in helping you think about how to improve your organization.

Related: Inquiring Minds, Improving Elementary Science by Linda LippeTransforming the Organization, Deming Podcast with David LangfordDeming Inspired Innovation in Education


Looking Back at Previous Posts on The W. Edwards Deming Institute Blog

Blogs are a convenient way to stay informed on topics you are interested in. They allow people to easily use an RSS reader to view recent posts that have been published as they have time.

One of the weaknesses in how blogs are used is that even active followers of a blog rarely seek out old posts that would be of interest and be useful to them. I think that often results in people missing out on information they would find worthwhile.

The Deming Institute blog offers several ways to help you find previous posts that you might find valuable. The category and tag links provide a way for you to find previous posts related to topics you are interested in. Some of the popular topics include: organization as a system, psychology, leadership, health care, data and education. There are many more topics; browse them on all of the left side of every page of our blog.

Search is another way to find old post you would value (the search feature is also found on the left side of all the pages on the blog).

And I will share a few selected old posts I think are interesting here:

We hope you enjoy our posts. If you have specific questions or topics you would like us to explore in future blog posts please let us know by commenting below.


Transformation: How to Apply SoPK

Transformation: How to Apply the System of Profound Knowledge (SoPK) presentation by Tripp Babbit at our 2015 research conference. Tripp also moderates our Deming Institute podcast.

Tripp discusses Kurt Lewin’s change model:

  1. unfreezing – overcoming “interim” and dismantling the existing midset
  2. changing
  3. freezing – adopting the new habit/way-of-thinking, the new way becomes what you expect and what makes you comfortable.

Tripp also discusses the idea of customer-in thinking; he learned this thinking from Peter Scholtes (our last blog post discusses the value of learning from a customer perspective).

He also touches on the psychological benefits of PDSA. Change often worries people. So while there are benefits to piloting on a small scale using PDSA to be efficient, effective and to reduce impact on customers of attempted improvements there is also the benefit that PDSA can help employees accept change more with less worry. The experience of the PDSA provides comfort in that the change has be tested. It isn’t as risky as change without experimental results showing the impact of that change within our own workplace.

Anyone can be the impetus for change, not just the CEO

David Langford discussed this well at a previous Deming conference, Change has to Start from the Top (that link phrase might seem to conflict with Tripp’s quote but follow the link to see that it does not). It is true that the management system has to support the ability of people to improve and institute change. What prevents most change for improvement is not the inability of most people to improve the systems in place but the management systems that prevent people from acting.

Related: People Take Time to Believe Claims of Changed Management PracticesBaking Apple Pies Using the Deming Management System (Deming podcast with Paula Marshall)Change Management: Create a Culture Seeking Continual Improvement, Don’t Just Use Band-Aids?


Some Notes on Management in a Hospital by W. Edwards Deming

We used to publish a newsletter. In the Fall 2006 Deming Interaction we published an excerpt from an article by Dr. Deming: Some Notes on Management in a Hospital (published in 1990 in the Journal of the Society of Health Systems).

In the lecture discussed from our last blog post I learned something I didn’t know (or had forgotten): Stu Hunter said that the precipitating event that caused W. Edwards Deming to go into the hospital (at the age of 89) was him being stabbed during a mugging.

The article by Dr. Deming chronicles a list of events that seem to point to the need for improvement of the processes in place at the hospital.

The man that designed the shower had obviously never used one. The shower head, when not held by hand, can only dangle and flood the floor. There is a tiny shelf in the shower big enough to hold only a wafer of soap. There is only one bar to hold on to. Use of this shower would be a risky business without a friend close by for rescue. Somebody sold somebody a bill of goods.

I haven’t had a hospital stay, but from my many stays in hotels I am disappointed how often basic consideration of the usability of the bathroom and shower seem to only be understandable if the species that designed the shower were not human and didn’t understand how they were used.

In one case Dr. Deming discovers he wasn’t given the drip that had been setup. He had to take the initiative to bring this to the attention of the head nurse:

The head nurse returned to say that the nurse that was to give the infusion had recorded the infusion as given. It is possible that she recorded it in advance, with the intention to give it, and did not correct the record. Is this the regular procedure, to record intentions? Who would know?

An unsuspecting physician, looking at the record for his patient, would assume that the infusion had been given, and could draw wrong inferences about how the patient had been doing on the drug. In my case, as it turned out, no harm. But how would he know? A nurse, or a physician, has a right to suppose that the medication was delivered as ordered and as recorded.

What is the purpose of the record? To inform the physician about intentions, or to tell him what happened?

As with all the many problems Dr. Deming found he saw the system failures. He understood the futility of blaming an individual for the natural result of bad systems.

Read the rest of this entry »


A Historical Look at Deming’s Career: Lecture by J. Stuart Hunter

Every year the American Statistical Association (ASA) selects an honoree to present a Deming Lecture at their annual conference.

The 2009 ASA Deming Lecture by J. Stuart Hunter, Princeton University: the first part of the lecture (20 minutes) is a historical look at W. Edwards Deming’s career and then it looks at the future of statistics.

Stu starts off the lecture talking about how he would pick up Dr. Deming from the train station and take him home when Dr. Deming came to Princeton University. He talked about how kind Dr. Deming was and the joy he took in playing with Stu’s kids. And he continued with how Dr. Deming’s demeanor was quite different in a professional setting where he would challenge those presenting. I think this pattern of a kind person who was very demanding on those with power and responsibility (whether they be professions, executives or CEOs).

Stu also talks about W. Edwards Deming work during World War II for the war effort. He talks about his efforts to encourage the adoption of Stewart’s statistical methods to improve quality during that time.

He discussed the successful efforts in post war Japan to create quality products and the struggles to do so in the post war USA. And then he mentions the 1980 broadcast of If Japan Can… Why Can’t We and the enormous impact that had in bringing quality management practices to the forefront in the USA.

His message was, you can’t blame the worker for the lack of quality, the person responsible for the lack of quality in the United States of American by golly are the managers – and he just chewed the managers out something fierce.

Stu is not related to me (in case you were wondering) but he did co-author Statistics for Experimenters with my father (Bill Hunter) and George Box.

Learn more about the ASA Deming Lecture committee including past lectures (including: Brian Joiner, Noriaki Kano, George Box, Gerald Hahn and Donald Berwick) and a nomination form on the ASA web site.

Related: The Art of Discovery (Lecture by George Box)The Development of Deming’s Management SystemInterview with Masaaki Imai


Red Bead Experiment Simulation

I ran across this simulation via a post on an e-learning web site. The community has challenges to create short simulations on various concepts and one of the challenges focused on the red bead experiment: the comments have links to various attempts. Remember these are created as an exercise by people that don’t necessarily have any experience with Deming’s ideas.

To learn about the lessons of the red bead experiment I suggest you consult these previous posts (which include videos with Dr. Deming): lessons of the red bead experiment: The Red Bead Experiment with Dr. W. Edwards Deming.

The simulation from Maija Perfiljeva includes some nice graphics and illustrates a bit of what can be learned from the red bead experiment. Do remember the simulations are just an exercise these participants created for fun.

The simulation does also show my prowess at making the best of the system I am put into:

screen shot of Red bead simulation - with foreman congratulating the best worker

As those of you with red bead willing worker experience will know (and the rest of you may have a hard time understanding) I am quite proud of my good results.

Read the rest of this entry »


My First Trip To Japan by Peter Scholtes

The Philadelphia Area Council for Excellence organized a tour to visit businesses Japan in 1985 and learn from them. 38 people participated in the trip including Peter Scholtes; William Hunter (my father); Brian and Laurel Joiner; Myron Tribus; and David and Carole Schwinn (David and Carole are presenting at our annual conference in September). Peter Scholtes wrote a report on the visit: My First Trip To Japan.

While in Japan the group also attended the JUSE Deming Award ceremony where W. Edwards Deming spoke.

Dr. W. Edwards Deming himself gave what was billed as a “special lecture” on the “Foundations for Success of Japanese Industry.” In fact, it was a scolding. He told the Japanese managers that they had an obligation to the world to uphold the finest of management techniques. He warned them that they were mistakenly allowing into Japanese companies the use of certain Western Management practices – such as management by objectives (MBO) and performance standards. These practices, Deming warned, are largely responsible for the failure of Western industry to remain competitive.

“Just as a healthy body can be brought down by an infection contracted from outside itself,” Deming admonished, “so too can Japanese management – the finest in the world – be infected by poor management practices imported from the West!” Using a blackboard, Deming then applied a statistically-based analysis to demonstrate how performance evaluation was fallacious. Deming’s performance was a tour-de-force; vintage Deming: wide-ranging inflections with his deep, booming voice, abrupt changes of pitch and pace, histrionic and profoundly true.

They visited numerous companies to learn from them.

Read the rest of this entry »