Deconstructing Deming I – Constancy of Purpose

File:W. Edwards Deming.gifMy 20 December 2013 post on W Edwards Deming attracted quite a lot of interest. The response inspired me to take a detailed look at his ideas 20 years on, starting with his 14 Points.

Deming’s 14 Points for Management are his best remembered takeaway. Deming put them forward as representative of the principles adopted by Japanese industry in its rise from 1950 to the prestigious position it held in manufacturing at the beginning of the 1980s.

Point 1. Create constancy of purpose toward improvement of product and service, with the aim to become competitive and to stay in business, and to provide jobs.

In his 1983 elaboration of the point in Out of the Crisis, Deming explained what he meant. Managing a business was not only about exploiting existing products and processes to generate a stream of profits. It was also about re-inventing those products and processes, innovating and developing to retain and capture market. Deming was fearful that management focused too much on short term profits from existing products and services, and that an effort of leadership was needed to reorient attention and resource towards design and development. The “improvement” that Deming was referring to is that through design and redesign, not simply the incremental improvement of existing value streams. Critically, Deming saw design and redesign as a key business process that should itself be the target of incremental continual improvement. Design and re-design was not an ad hoc project initiated by some rare, once in a generation sea-change in the market or motivated by a startling idea from an employee. It was a routine and “constant” part of the business of a business.

Some of Deming’s latter day followers sometimes deprecate the radical redesign of processes in approaches such as Business Process Re-engineering, and instead promote the incremental improvement of existing processes by those who work in them. That is exactly the approach that Deming was warning against in Point 1.

It is worth recalling the economic and geographic climate within which Deming put forwards this principle. During the early 1980s, the US and Western Europe suffered a significant recession, their populations beset with the dual evils of unemployment and inflation. The economic insecurities were aggravated by social unrest in the West and the intensification of the Cold War.

In 1980 Robert Hayes and William Abernathy, academics at the Harvard Business School, attacked US management in their seminal paper Managing our Way to Economic Decline. They found that fewer and fewer executives were from engineering and operations backgrounds, but increasingly from law and finance. Such managers had little understanding, they said, of the mechanics of the businesses they ran or the markets in which they competed. That in turn led executives to tend to pursue short term profits from existing value streams. These were easy to measure and predict on the visible accounts. However, managers were allegedly ill placed to make informed decisions as to the new products or services that would determine future profits. The uncertainties of such decisions were unknown and unknowable other than to a discipline specialist. Franklin Fisher characterised matters in this way (1989, “Games economists play: a noncooperative view” Rand Journal of Economics 20, 113):

Bright young theorists tend to think of every problem in game theoretic terms, including problems that are easier to think of in other forms.

This all appeared in contrast to Japanese manufacturing industry and in particular Toyota. By 1980, Japanese manufactured goods had come increasingly to dominate global markets. Japanese success was perceived as the (Lawrence Freedman, 2013, Strategy: A History, p531):

… triumph of a focussed, patient, coherent, consensual culture, a reflection of dedicated operational efficiency, or else a combination of the two.

Certainly in my own automotive industry days, my employer had come to see its most successful products literally as commodities. They belatedly realised that, while they had been treating them as a mere income stream, admittedly spent largely on unsuccessful attempts to develop radical new products, Japanese competitors had been filing dozens of patents each year making incremental improvement to design and function, and threatening the company’s core revenues.

But did Deming choose the right target and, in any event, does the exhortation remain cogent? It feels in 2014 as though we all have much more appetite for innovation, invention and product design than we had in 1983. Blogs extol virtues of and strategies for entrepreneurship. Slogans proliferate such as “Fail early, fail fast, fail often”. It is not clear from this web activity whether innovation is being backed by capital. However, the very rate of technological change in society suggests that capital is backing novelty rather than simply engaging in the rent seeking that Hayes and Abernathy feared.

In 2007 Hayes reflected on his 1980 work. He felt that his views had become mainstream and uncontroversial, and been largely adopted in corporations. However, information and globalisation had created a new set of essentials to be addressed and to become part of the general competencies of a manager (“Managing Our Way… A Retrospective by Robert H. Hayes” Harvard Business Review, July-August 2007, 138-149).

I remain unpersuaded that there has been such a broadening in the skill set of managers. The game theorists, data scientists and economists seem to remain in the ascendancy. Whatever change of mind in attitudes to design has taken place, it has happened against a background where CEOs still hop industries. There are other explanations for lack of innovation. Daniel Ellsberg’s principle of ambiguity aversion predicts that quantifiable risks that are apparent from visible accounts will tend to be preferred over ambiguous returns on future inventions, even by subject matter experts. Prevailing comparative advantages may point some corporations away from research. Further, capital flows were particularly difficult in the early 1980s recession. Liberalisation of markets and the rolling back of the state in the 1980s led to more efficient allocation of capital and coincided with a palpable increase in the volume, variety and quality of available consumer goods in the West. There is no guarantee against a failure of strategy. My automotive employer hadn’t missed the importance of new product development but they made a strategic mistake in allocating resources.

Further, psychologist Daniel Kahneman found evidence for a balancing undue optimism about future business, referring to “entrepreneurial delusions” and “competition neglect”, two aspects of What you see is all there is. (Thinking, Fast and Slow, 2011, Chapter 24).

In Notes from Toyota-Land: An American Engineer in Japan (2005), Robert Perrucci and Darius Mehri criticised Toyota’s approach to business. Ironically, Mehri contended that Toyota performed weakly in innovation and encouraged narrow professional skills. It turned out that Japanese management didn’t prevent a collapse in the economy lasting from 1991 to the present. Toyota itself went on to suffer serious reputational damage (Robert E. Cole “What Really Happened to Toyota?” MIT Sloan Management Review, Summer 2011)

So Deming and others were right to draw attention to Western under performance in product design. However, I suspect that the adoption of a more design led culture is largely due to macroeconomic forces rather than exhortations.

There is still much to learn, however, in balancing the opportunities apparent from visible accounts with the uncertainties of imagined future income streams.

I think there remains an important message, perhaps a Point 1 for the 21st Century.

There’s a problem bigger than the one you’re working on. Don’t ignore it!


George Box and Response Surface Methods

News of George Box’s death escaped me while I was on vacation earlier this year and I thought it about time I commented on a huge statistical career. There are plenty of thorough obituaries on the web and I’m sure that the RSS will do a splendid job in due course. It is sad that there was no obituary in the Fleet Street press for somebody who has made such an eminent contribution to science and technology. Box’s particular talents were formed through his English training and learning on the job. Perhaps his neglect on the national stage is a measure of the extent to which the biggest ideas work gradually and organically, away from the grandstanding of the celebrity culture.

The word statistician feels inadequate to describe Box’s work. He was a man actively engaged in seeking novel methodologies for solving practical problems. Many of his solutions embraced what we conventionally think of as statistics. However, his work always seems that of somebody who looked for methodological solutions and sometimes found them in statistics, rather than a statistician looking to sell his product. Box described himself as “an accidental statistician” and I have a soft spot for people who arrive at their destinations by unconventional routes.

I was spurred on to reflect on Box’s work by Tim Davis’ worthwhile advocacy of dimensional analysis in experimental design;. Box himself lamented that engineers are often hypnotised when adopting statistical tools and discard their engineering knowledge in the process with little regret. There is a gap between the engineer incubating a, possibly ill-formed, problem and a statistically inspired structured investigation. Sometimes it’s a hazardous leap between the two. From the far side it’s sometimes difficult to look back and see what motivated the investigation. The more bridges we can find across that gap the better. I think few have approached the effectiveness with which Box pontificated (in the exact sense of the word).

One of Box’s greatest contributions was his advocacy of Response Surface Methods (“RSMs”). I think some of my most enjoyable statistical experiences were back in my automotive industry days when we were using RSMs with computer models to optimise design details on mechanical components. We were looking to improve durability and reduce warranty costs. I recall one situation where we exploited an elastic-plastic model of a feature that took 16 hours to run on the company’s CRAY supercomputer, a situation where even computer experiments needed a structured investigation.

As I said, Tim had got me thinking and I returned to a frustrating book that I have put down years ago: Walter G Vinenti’s What Engineers Know and How They Know It (1990, Johns Hopkins UP). Vincenti was an eminent aerospace engineer and the book is a fascinating history of a number of notable events in aerospace design. I do have a problem with this book. Vincenti seems rather dismissive of statistics. There are no statisticians in the index! There is however a compelling chapter on W F Durand and E P Lesley’s First World War propeller experiments. These were executed through quite a nice little factorial design. Durand’s trials and tribulations in managing the experimentation show that really the statistics is the easy bit. You can find the full report here. It is well worth reading.

Vincenti is rather dismissive of Durand’s statistical skill and relegates it to a footnote. He doesn’t really acknowledge Durand’s methodological sophistication. The truly frustrating thing about the book is the difficulty in drawing generalised conclusions that answer the question in the title. However, Vincenti does come up with the suggestion that “parameter variation” in the broadest sense is a key part of the engineering learning process. I think it’s a disappointing takeaway as his descriptive part of the book is much richer than the conclusion suggests. Perhaps I will come back to this.

One of Box’s key insights was engineers’ need for immediacy and sequentiality in the parameter variation process (“Statistics as a Catalyst to Learning by Scientific Method Part II – A Discussion”, Journal of Quality Technology, 31(1), 1999, pp16-29).

Psychologist Daniel Kahneman has described two ways of thinking that typify human decision making. System 1 is instinctive, fluent, heuristic and integrated with the experience base. System 1 is over confident and often leads us astray. System 2 employs reflective considered analysis. It can, when properly guided by statistical theory, guard against the hazards of System 1. Problems such as “What factors determine this process output?” are difficult. Kahneman observes that often, when confronted with difficult problems, System 1 substitutes a simpler problem such as “What factors are we currently relying on to control this process?”. Experts think they are answering the first question when they are in fact answering the second. Box’s requirement for immediacy allows engineers to exploit their, sometimes misleading, experience base while subjecting it to a rigorous experimental test in a rapid and efficient manner.

Experimental results feed into System 2 thinking. However, the human mind is still much too confident in adopting explanations that are in reality merely plausible rather than probable. The requirement of sequentiality allows analysis of those explanations in a rich and diverse context that puts them to a rigorous test.

One of the fascinations of engineering research is exploring the partially known. Jon Schmidt made the following remark about structural engineering but I think it applies to engineering in general. I t certainly applied to mechanical engineering in my automotive days.

Structural engineering is the art of modelling materials we do not wholly understand into shapes we cannot precisely analyse so as to withstand forces we cannot properly assess in such a way that the public at large has no reason to suspect the extent of our ignorance.

The application of statistics, and in particular RSMs, to engineering is one of the great tools we have for decision making under uncertainty. Modern psychology has tended to confirm Box’s instincts, learned on the job, about the tools that best support human decision making and guard against its inadequacies. Box remains a role model in developing strategies for operational excellence.