From Davis Balestracci -- What Part of "Never" Don't People Understand?

Published: Mon, 01/24/11

From Davis Balestracci -- What Part of "Never" Don't People Understand?

Are You Treating Special Causes as...Special Causes?

 [~1000 words -- Take 5-7 minutes to read over a break or lunch]
If you would like to read this on-line:
Hi, Folks,
I am so sick of patronizing articles touting how WONderful control
charts are...that then proceed to bog down heavily in the mechanics of construction and minutiae of interpretation, meanwhile losing the poor readers in the process (I've had to review several...and they give ME a headache!). 
And then there are the inevitable torturous discussions of "special cause tests":  all NINE of them.  No wonder people continue to use things like...trend lines.  But, I'm getting ahead of myself.
First of all, before you take another "tools" seminar or read another book, find something important and plot it over time.  This is probably the only way to learn the most important lesson of quality improvement.  As I have relentlessly tried to make clear, you are swimming in everyday opportunity.  So, take Dr. Don Berwick's advice (opening quote in the newsletter below): .
Many people have the misconception that each special cause signal on a chart must be treated as a "special cause" (needs to be uniquely investigated) as opposed to "common cause" --  Have you ever thought, "Might there be one underlying explanation generating all of these signals?"
How ironic that a lot of people teaching control charts as a tool don't "get" this more subtle manifestation of common versus special cause.  I heard a wonderful saying once:  Quality improvement is about a MIND set, not a tool set.  And, I would add, it is a mind set that knows how to ask the right questions.

"Trend" -- the Display that Won't Die

Someone once presented me with the graph below (Yes, the y-scale started at "0").  It almost convinces you that there is a trend, eh? 

Some of you could be wondering, "What insight might a control chart give?"  Here you go:

TEST 1. One point more than 3.00 standard deviations from center line.

Test Failed at points:  9, 50, 51, 52


TEST 2. 9 points in a row on same side of center line.

Test Failed at points:  9, 10


TEST 5. 2 out of 3 points more than 2 standard deviations from center line (on

     one side of CL).

Test Failed at points:  4, 6, 7, 9, 15, 48, 49, 50, 51, 52


TEST 6. 4 out of 5 points more than 1 standard deviation from center line (on

     one side of CL).

Test Failed at points:  5, 6, 7, 8, 9, 10, 17, 18, 20, 50, 51, 52


TEST 8. 8 points in a row more than 1 standard deviation from center line

     (above and below CL).

Test Failed at points:  9, 10

YIKES:  Sixteen of the 52 data points generate special cause
signals (some data points even generate multiple signals): 
30 special cause signals total!  Where does one begin?
Unfortunately, the way I see control charts generally taught,
"obviously," one should initially investigate, individually, the four points outside the three standard deviation limits (Observations #9 & 50-52)...NOT!
As many of you know, over the years, I have developed an increasing affection for the much-neglected run chart -- a time plot of your process data with the MEDIAN drawn in as a reference line.  It is "Filter #1" for any process data and answers the question, "Did this process possibly have at least one shift during this time period?" This is generally signaled by a clump of eight consecutive points either all above or below the median or, less often, by six consecutive increases or decreases (indicating a transition to a new process level). 
[Any good software package should do this analysis and let you effortlessly toggle between run charts and control charts]
If special causes are observed in the run chart, then it makes no
sense to do a control chart at this time because the average of all
this data doesn't exist
-- Sort of like, "If I put my right foot in
a bucket of boiling water and my left foot in a bucket of ice water,
on the average, I'm pretty comfortable." 
One of the healthiest things that a run chart can do is get you thinking in terms of "process needle(s)" -- i.e., focusing on the process's
"central tendency." 
Most of the time, run charts are glossed over and taught as the
"boring" pre-requirement to learning control charts.  I mean, isn't
it far more exciting to jump right to the control chart, with all its bells and whistles, of all the data, look at the special cause signals, and, as previously mentioned, try to find reasons for each individual signal? 
The run chart does not find individual special cause observations
because that is not its purpose.  That is the objective of the
control chart: "Filter #2" -- plotting the data incorporating the shifts detected via the run chart, which then usually reduces the number of subsequent special cause signals, resulting in a lot less confusion.

The control chart also has an additional power to detect more subtle shifts neither obvious nor detectable in the run chart (future newsletter).
So, what light might a run chart shed on the current situation?

With the y-axis scale a lot healthier and not having control limits
as a distraction, doesn't it look like the "needle" shifted
twice -- around observation #21 and observation #47?  In fact, when I asked the clients about those two particular points and their corresponding dates, they looked at me like I was a magician and
asked, "How did you know?"  Those dates coincided with two major interventions to improve this process. 
As the chart shows, they worked -- two "needle bumps"...NOT a continuously increasing improvement "trend"!  Making only those two adjustments, the correct resulting control chart is shown below...with not a special cause to be found (and a possible improvement/transition in the making as evidenced by the last four data points -- time will tell).

[For those of you who might like to reproduce this analysis, the data are contained in the attachment to this e-mail]

Take "the Challenge" 

1. Can you think of one or two applications like this in your everyday work or meetings?  Plot it!
2. Can I also challenge you to take one routinely "trended" data display and plot it as a run chart? 
3. Will you promise me that, before you take yet another course on more "tools," you will do a (mere) run chart of a number that makes you "sweat"?
4. "What part of 'NEVER'..." -- If someone asks you to "trend" some
data, will you flat out refuse...then also refuse their valiant attempt to keep the trend monster alive via the dreaded "two-headed transplant" technique when they predictably insist, "OK, then...just put them both on the same page"?
And, for those of you who have resolved to drive out data INsanity in 2011, would you please share with me your experiences with the four challenges above?
Until next time...
Kind regards,
P.S. My Other Challenge Still Stands, Too:
Interested in Becoming One of the "20%"?
[Not sure what I mean?  See:
Sorry to be a little repetitious, but I'm working on a web site revision (stay tuned), and I have become even more convinced that quality professionals do not get the respect they deserve.  The article above demonstrates my overall approach to education / consulting, and I would love to partner with some of you to take your careers (and results!) to the next level:  "a quantum leap to unprecedented results," one might say.
Might you consider...
========================================================= initial 3-month mentoring process with me using my book as a guide -- with two
scheduled phone conversations a month and unlimited e-mail access?
Contact me to discuss.  I am also open to mentoring an ongoing group of individuals
from an organization.
For those of you, especially those who attended the recent IHI Forum, who have purchased my book, my sincere thanks.  I want your HONEST feedback as to its practicality and always welcome suggestions for newsletter topics.
Data Sanity: A Quantum Leap to Unprecedented Results can be ordered via:
My publisher (MGMA) is giving an "IHI special" 15% discount until the end of this month if you order through the link above.  ENTER "DAVIS" AT CHECKOUT.
It is also available through
(Thanks, Dr. Steve Tarzynski, Dean Spitzer, Adam Lennox, and Mike Taigman for your very kind Amazon reviews).
[Foreign subscribers (or anyone having problems with either link) would probably be best contacting Marilee Aust directly at: .  I promise you excellent service.]
--As many of you know, I do a lot of public speaking and love sharing my passion.  My 2011 schedule is currently WIDE open.  Might you consider a lively, challenging plenary presentation for your professional society meetings giving an overview of holistic improvement, data sanity, or the psychology of culture change?
Please have the appropriate organizers contact me during the planning.
--How much longer can we as a profession sit on our hands and wait for execs to "get" it? The time is NOW for executives to go beyond "passionate lip service" to integrating quality into the organizational DNA.  This will take intense, ongoing dialogue between quality professionals and management.
I would love to create and build strong partnerships with people like YOU to make this happen...and I have just the leadership retreat -- and follow-up -- to do it!  Shall we plan together?
Or should part of the planning be an "away day" with your staff to set you up for subsequent success...or even do some common cause analyses that save your organization a million or two?  MIGHT that get the execs' attention?  Contact me for more information.
Was this forwarded to you?  Would you like to sign up?
If so, please visit my web site -- -- and fill out the box on the home page then click on the link in the confirmation e-mail you immediately receive.