The One Rare Leadership Skill that Trumps EVERY Tired, Recycled Platitude: the HUMILITY Resulting from a BASIC Understanding of "Variation"
Davis Balestracci
Improvement Consultant / Public Speaker / Author of Data Sanity: A Quantum Leap to Unprecedented Results
Doing the Red Bead Experiment and spouting "Joy in work!" is the coward's way out
[For the background to this analysis, see Pondering Leadership “Gurus”]
In a 2006 major plenary speech, a former colleague, known for his love of the Deming philosophy and now a world leader in quality (WLQ) (and who spoke at a recent Deming Institute conference), presented the following bar graph showing a comparison of the sum of rankings for 10 aspects of 21 counties in a small country's healthcare system (considered on the cutting edge of quality). Lower sums are better:?Minimum = 10, Maximum = 210, Average = 10 x 11 = 110.
He even mentioned something about “quartiles.”
My antennae went up. A Deming proponent??A bar graph??With absolutely no context of variation for interpretation??Quartiles? And a?literal?interpretation of the rankings??
Envision a meeting to discuss the rankings, possibly revise them, and then decide on how to take action. We've all been at these types of meetings:
I’m reminded of a favorite saying of Dr. Deming:
“Off to the Milky Way!”
The situation is analogous to the Red Bead Experiment!
I was able to locate the raw data. I won’t bore you with the details of the statistical analysis, but it did indeed strongly demonstrate the presence of differences.?So, how does one go about finding them? Using an exact analog to the analysis used by Dr. Deming in the red bead experiment, more formally called Analysis of Means (ANOM):
Note that the points are not connected (there is no time order), and I chose the horizontal axis order to go from smallest score to largest.?"3" standard deviation limits are used as common cause limits (as in the red bead experiment comparing workers) – in this case, 110 +/- 55 (55 to 165).
The statistical interpretation: (1) there are two counties' performances "outside the system" (Deming's nomenclature) – County #1 is superior and County #21 sub-par compared to their counterparts; (2) the other 19 counties are, based on this data,?indistinguishable?("in the system")!?
Also,?there is neither a “top” quartile nor a “bottom” quartile.
In his book The New Economics, Dr. Deming shows a similar chart and writes a comment on it about the performance equivalent of counties 2 to 20:?
“These cannot be ranked!”?
The purpose of ANOM is to expose any hidden special cause variation in existing components of a common system. Dialogue then ensues about how to reduce any?inappropriate and unintended variation?(County 21) while investigating whether there are possible lessons to be learned by studying beneficial variation (County 1) – that could improve the quality?of the entire system.
Another possible common cause strategy would be to find criteria to somehow "color code" the performances inside the limits ("stratification") to see whether there is a clustering pattern tendency for the higher scores and/or lower scores. There may be patterns (will allow focus)... or not (issues are "systemic"), which is still helpful information. Sure beats a Ouija board, doesn't it?
A potentially exciting transformation opportunity...not recognized
I decided to share this analysis and my observations with my former colleague and was surprised and delighted when he responded. However, I was?shocked?at his total lack of comprehension – TOTAL! Our verbatim e-mail correspondence follows.
World quality leader (“Now that I’m famous, I need to be political and make darn sure no one is offended, especially those itty bitty executive egos.”):?"A subtle issue you did not tackle is the political-managerial issue of communicating such insights to [the two special cause counties] and the counties that thought they were 'different,' but, statistically, aren't. I wonder what framework one could use to approach that psychological challenge."
Davis (“Oh, for heaven’s sakes! Why do executive have such thin skins while making six-, seven-, or even eight-figure salaries... and you making $40K per speech!”):?"As I say to my audiences, 'Hey...I'm just the statistician, Man!'
"I'm going to be very hard on you here, but I think the issue is how people and leaders like?you?are going to facilitate these difficult conversations...which will be profoundly different...and productive!?This is the?leadership?that quality gurus keep alluding to...and seems to be in?very?short supply.
"My?job is to keep you all out of the 'data swamp'; however, I would be a very willing participant.?I have a saying, 'I'm the statistician, I know nothing.?You're the [leaders], you know too much.?That makes us a?great?team!'
"And I would love to pilot some of these types of analyses with you or other leaders – we need to figure out what this process should be. This is potentially very exciting and could quantum leap the quality improvement movement.
"My point is that this 'language' needs to be a?fundamental?piece of?any?improvement process...and led by leaders who understand it and are now promoted into positions of leadership?only?if they understand it.?If this could become culturally inculcated, then the ongoing daily defensiveness reacting to data stops...PERIOD!
"The discussion will then focus, as it should, on?process.
"I am seeing far too much concern about 'hurting people's feelings.' This would change that as well as have conversations leading to appropriate action.
领英推荐
"That's what I've been saying the last few years – we need?new?conversations... and this could be a key catalyst."
[I guess this is why I never got "famous"... ]
World quality leader (well-rehearsed, well-honed insincerely sincere patronizing pat-on-the-head schtick to pass the buck on facing reality):?"Nope. I don't buy it. Yes, I am a leader and need to carry the message.?But I know you too well to let you off the hook. I'd love to see you try to lead these conversations and experiment with approaches. You're a leader, too."
Davis (“OK, I see your game, but I’m game!”):??"Give me an opportunity and I will do my best to lead that conversation… and feel that we could begin by co-facilitating it… and you can have all of the credit!?Have you fathomed the potential of this?"
World quality leader: [Crickets…]
That last e-mail has never been answered. At his insistence at the time, I sent the analysis with explanation to the original executive group who collected and summarized the data.?No reply.
Here it is, over 15 years later, and several follow-up gentle e-mail reminders have been ignored (including a teasing “Remember this?” a couple of years ago). I've given up any hope of participating in what would have truly been a groundbreaking transformational educational opportunity.?And I've had no more luck persuading any other leader to give it a try.
Bottom Line:? Many people (even those who do the red bead experiment) who think they "get" Dr. Deming's message, quite frankly, don't... and don't really want to.
This example's statistical?simplicity?is what Dr. Deming demonstrated in his seminars (and, once again, the red bead experiment is an ANOM!).?After 30+ years of trying to teach similar things with real data (see links at end of this article), I am still amazed at the walls of?FIERCE?resistance put up by (alleged) leaders and resulting hostility due to clueless ignorance and arrogance.
How can any leader in good conscience abdicate the responsibility to comprehend the liberating transformational power of a simple understanding of variation – at the cost of tolerating the confusion, conflict, complexity, and chaos caused by countless Ouija board data meetings?
Is that too much to ask of someone making a huge salary whose actions affect the "five-figure salary" folks?
The all too easy takeaway from the red bead experiment is to embrace its audience as victims and patronize them with the overly simplistic "You need 'Joy in work!'" platitude. That is only a secondary, tangential lesson. The real lesson has been lost:
The need is for?an even deeper understanding of variation?to create leadership?humility?that will in turn create the joy.
How many leaders are willing to?own?and deal with the lack of "Joy in work!" caused by confusion, conflict, complexity, and chaos (and for some, their "tantrums") due to lack of a BASIC knowledge of variation in "the everyday use of data" process?
This remained the underlying source of Dr. Deming's unforgiving curmudgeonliness until the end of his life.
To use a favorite quote of (alleged) leadership gurus: "I'm getting tired of excuses."
================================
If you want another everyday example of this type of analysis (I will not be held responsible for any discomfort this causes :-) ):
Your everyday work experience has a much broader application beyond ANOM (You might need to lie down with a cold compress after reading this one)
You are NOT a "victim" of all this and can do something it about right now: Start here
Amusing note: ?My own state of Maine had a panicked headline in the newspaper: ?"Maine's ranking drops from 13th to 17th" in some state indicator, and the article was full of finger-pointing and blame for the reasons why. I wonder on whom the Ouija board finally settled? ?Common cause or special?
========================================
Regardless of your improvement approach, Chapters 1 to 4 of my book Data Sanity teach a robust, results-oriented leadership philosophy designed to catalyze transformation to a culture of excellence
Read Rip Stauffer's review, published in Quality Digest
For UK readers who want a hard copy, it is available?on Amazon UK
An ebook version is available through the publisher
?
I help organizations and leaders drive continuous improvement and spark innovation through Lean management, building a culture of learning from mistakes, and fostering psychological safety. 3 Shingo Book Awards.
1 年A line / run chart would be a must for time-series data, but when comparing snapshots in time across different countries or organizations, I thnk that's one appropriate use of a bar / column chart. That said, failing to distinguish between the "noise" of similar outcomes vs. true statistical outliers... to me, that's the thing worth criticizing more vociferously. "Also, there is neither a “top” quartile nor a “bottom” quartile." and "These cannot be ranked." Those are rare insights that I wish every leader understood.
Management / Quality Consultant “The measure of quality, no matter what the definition of quality may be is a variable.” (Shewhart, 1931)
1 年Plotting the dots is definitely the way to get things done and learn about your processes as never before. Not sure this leadership skill is rare-I’ve never seen it in person-like a unicorn, mythological! Thanks for helping me get on track.
Owner at Leaders Get Results, LLC
1 年I always learn something from your posts. You are a national treasure.
VP Operations
1 年Davis, there seems to be a couple of ANOM variants?
Six Sigma Freelance Consultant at Sigma Solutions
1 年Thanks again for sharing your experience. "'I'm the statistician, I know nothing. You're the [leaders], you know too much. That makes us a great team!'" Love it ! I like to stress that "Bad news is good information". Unfortunately, the discovery of bad news is rarely welcome by Management... and so, often gets hidden from the reports whenever possible. Instead, should not we collect data in a way to maximize the chances to find those assignable bad news hidden somewhere inside our Process or Products ? (instead of collecting data to "prove" that our Process or Product is innocent...). Soon or later anyway, someone will find out... and it'd better be us than our customers (not to mention the competition...).. To do so, capturing and analyzing Variation, applying Common Cause/Special Cause thinking, seems a great place to start! "Good morning, what bad news do you have for me today ?"