SlideShare une entreprise Scribd logo
1  sur  75
Télécharger pour lire hors ligne
Deming’s Red Bead
   Experiment

 AICE Quality Conference
    Tuesday, 06MAR07

         Jim Clauson
   Breakthrough Systems
  http://jclauson.com/aice

    © 2007 Breakthrough Systems
                             1
Why Are We Here?
To consider:

• what the Red Bead Experiment is,
• what it has to do with quality and
• how it can have an impact on your
  everyday quality activities


               © 2007 Breakthrough Systems
                                        2
Session Agenda
   The Red Bead Experiment
   Numeracy
   System of Profound Knowledge
   Finding Red beads
   Impact of psychology
   Charting red beads
   “What will you do on Monday?”
             © 2007 Breakthrough Systems
                                      3
Introductions and Expectations
• If you are sitting with someone you
  know, please move
• You will interview, then introduce the
  person next to you
• Who they are, something unique or
  interesting, what industry they
  represent, and what their expectations
  are today

             © 2007 Breakthrough Systems
                                      4
Run Red Bead Experiment
• Click [here] for the red bead slides.




              © 2007 Breakthrough Systems
                                       5
Review: Why Are We Here?
To consider:

• what the Red Bead Experiment is,
• what it has to do with quality and
• how it can have an impact on your
  everyday quality activities


               © 2007 Breakthrough Systems
                                        6
Beyond Red Beads
• Red Beads Everywhere, oh my!!
• Finding those red beads
  – Red, white and non-red?
• Quantifying those read beads
  – Hit by a car –vs- bump a file cabinet
• Eliminating those red beads
  – 99.99999999999999999999999999%

               © 2007 Breakthrough Systems
                                        7
Numeracy
• an ability to handle numbers and other
  mathematical concepts
• in the US, it is somewhat better known
  as Quantitative Literacy
• innumeracy is a lack of numeracy




             © 2007 Breakthrough Systems
                                      8
3 Kinds of Numbers for
         Management.
• Facts of life. If we don't make this profit
  figure, we will go out of business.
• Planning, prediction and budget. Can be
  used to compare alternative plans.
• Arbitrary numerical targets. Generally used
  to judge workers.

Avoid the use of the 3rd kind of number

          Henry Neave The Deming Dimension
               © 2007 Breakthrough Systems
                                        9
Data Sanity
We can either react to numbers, with
 explanations of every percent change, with
 the inherent frustrations, fear, and failure
Or
We can understand our data, put it to good use,
 and apply valid management principles

The choice is ours.

               © 2007 Breakthrough Systems
                                        10
Through the Lens of SoPK
         System of Profound Knowledge

•   Appreciation for a system
•   Knowledge about variation
•   Theory of Knowledge
•   Psychology

From The New Economics, Deming
                © 2007 Breakthrough Systems
                                         11
1 of 4: Appreciation for a
             System
• Pay attention to interactions more so
  than components
• Knowledge of statistical variation more
  so than discrete numbers
• Long term focus more so than short
  term
• Cooperation more so than fear, blame
  and internal competition

             © 2007 Breakthrough Systems
                                      12
1 of 4: Appreciation for a
             System - II
• “94% of the outcome of any organization
  comes from the processes used, not the
  people”.
• “A fault in the interpretation of observations,
  seen everywhere, is to suppose that every
  event is attributable to someone (usually the
  one closest at hand), or is related to some
  special event. The fact is that most troubles
  with service and production lie in the system
  and not the people”.

                © 2007 Breakthrough Systems
                                         13
2 of 4: Knowledge of Variation
• You have experienced the Red Bead
  Experiment
• The Theory of Variation is at the core of cost
  savings, Kaizen, 6 sigma…
• Dr. Deming’s early works focused on
  statistical variation. He added the rest of the
  SOPK in the last 10 years of his life.
• Stable System versus Unstable System

                © 2007 Breakthrough Systems
                                         14
Variation: Deterministic –vs-
           Probabilistic
• Deterministic - linear, cause and effect
  sequences. If you do this, that will happen.
• Probabilistic - exact time, location, and effect
  is random. e.g. Number of Red Beads.
• Treating a probabilistic result as if it was
  deterministic will cause problems
• Past results will not guarantee future results



                © 2007 Breakthrough Systems
                                         15
Variation: Can we predict?
• Engineers often predict accidents. Their predictions
  are uncanny for correctness in detail. They fail in
  only one way – they can not predict exactly when the
  accident will happen.
       - Dr. Deming, Out of the Crisis page 479
• Calculations after the fact, using only data available
  prior to the disaster, showed there was greater than a
  10% chance of the Challenger explosion occurring,
  given the pre-launch temperatures and prior history
  of O-ring burn through.

                  © 2007 Breakthrough Systems
                                           16
3 of 4: Theory of Knowledge - I
• Knowledge is based upon prediction
• Knowledge is built on theory
  – Chanticleer the barnyard rooster
  – Actions taken without theory lead to losses
• Use of data requires prediction
• There is no true value of a measurement, it
  depends on methods, context, and use
• Operational definitions are necessary

                © 2007 Breakthrough Systems
                                         17
Operational Definitions - I
• “Clean the table…




              © 2007 Breakthrough Systems
                                       18
Operational Definitions - II
• Most arguments about conflicting data
  come down to the definition of how to
  count the data
• Try to be precise in your definitions, but
  likely something unforeseen will arise
• The beads were:
  – red & white or red, white & non-red?

              © 2007 Breakthrough Systems
                                       19
Deming said…
• “It’s absolutely vital for business that
  you settle this method of counting,
  measuring, definition of faults,
  mistake, defect, before you do
  business. It’s too late afterwards”
-Dr. W. Edwards Deming



             © 2007 Breakthrough Systems
                                      20
4 of 4: Psychology
• Extrinsic versus intrinsic motivation
• People will use the charts you make - up and
  down the organization
• If you do not understand the people &
  understand psychology, the charts will be
  ignored
• Competition, fear, perceptions, loss of control
  change the data and the chart’s message

                © 2007 Breakthrough Systems
                                         21
Through the Lens of SoPK
          System of Profound Knowledge

•   Appreciation for a system
•   Knowledge about variation
•   Theory of Knowledge
•   Psychology
•   Thinking about all 4, we’ll concentrate on
    identifying and quantifying variation
                 © 2007 Breakthrough Systems
                                          22
Red Beads:
Find, Quantify, Reduce




     © 2007 Breakthrough Systems
                              23
Take a Step Back:
         Systems Thinking
•   Process viewed as a system
•   SIPOC
•   The “new” 4M’s
•   Psychology: Suboptimization
•   Remember the “94/6 Rule”
•   Using SPC


              © 2007 Breakthrough Systems
                                       24
Production Viewed as a
       System




     © 2007 Breakthrough Systems
                              25
SIPOC
•   Supplier
•   Input
•   Process
•   Output
•   Customer



               © 2007 Breakthrough Systems
                                        26
The “new” 4M’s
•   Old: man, machine, material, method
•   Measurement added
•   Person or people replaces man
•   Equipment replaces machine
•   Supplies is used for material
•   Process is used for method
•   Environment added
    – Physical and mental

                 © 2007 Breakthrough Systems
                                          27
Group Activity - IV
• As individuals, draw a SIPOC diagram
  for your job
• See if you can identify all of the new
  4M’s as inputs to your process
• Compare and discuss as teams
• Choose the 3 most interesting to report
• Save this work, it will be used later

             © 2007 Breakthrough Systems
                                      28
Psychology: Suboptimization
• We assume that optimizing a system
  considers all the sub-parts
• One unit may be selfish and take an
  action that makes them look good, but
  hurts others
• One process may shift problems down
  the line to let others have to worry about
  it

              © 2007 Breakthrough Systems
                                       29
No Gold Stars Here
• Awards, bonuses, gold stars can
  actually have a detrimental impact
• For a person driven extrinsically, each
  subsequent reward must be larger in
  order to have the same impact
• Creation of winners and losers
     http://www.alfiekohn.org/index.html

                © 2007 Breakthrough Systems
                                         30
Group Activity - V
 Game: Win As Much As You Can

A Decision Making Exercise,
Illustrating the Effects of Human
Behaviors and Psychology on
Performance Measures
             [link] to game

           © 2007 Breakthrough Systems
                                    31
The “94/6%” Rule
• It is critical to separate system causes
  from individual causes of variation
• Deming started at 85% systems and
  15% worker and had moved up to 96%
  and 4% by his death
• What are the implications of the 96/4%
  Rule?

             © 2007 Breakthrough Systems
                                      32
Breather – We OK?
•   What have we addressed?
•   Numeracy
•   System of Profound Knowledge
•   Looking at your work as a system
•   Suboptimization exercise
•   96/4% Rule
•   We OK?
               © 2007 Breakthrough Systems
                                        33
Statistical Process Control
• Control Charting provides knowledge of
  variation
• a lens, providing a different way of
  viewing the world
• a significantly different view of what is
  happening than will other methods


              © 2007 Breakthrough Systems
                                       34
A Basic Control Chart
                            Injuries per Month - as a Control Chart

25
20
15
10
5
0                                                                            May-04




                                                                                                                                   May-05
                       May-03
              Mar-03




                                                  Nov-03



                                                                    Mar-04




                                                                                                        Nov-04



                                                                                                                          Mar-05
     Jan-03




                                Jul-03




                                                                                      Jul-04




                                                                                                                 Jan-05
                                                           Jan-04
                                         Sep-03




                                                                                               Sep-04
                                         © 2007 Breakthrough Systems
                                                                  35
SPC Basics
•   Common -vs- special
•   System in control?
•   System predictable?
•   What about psychology?




              © 2007 Breakthrough Systems
                                       36
Charting the Red Beads
• In the Red Bead Experiment, we
  reacted to the random noise from
  result to result.
• Rewards, punishments, ranking of the
  workers, feedback to the workers had
  no effect on the results of the process.
• The process was stable and needed
  to be changed!

              © 2007 Breakthrough Systems
                                       37
Stable –vs- Unstable
• Stable processes contain only common
  cause variations and are predictable
• Unstable processes contain special
  cause variations and are not
  predictable.
• Only predictable processes may be
  used to plan effectively

            © 2007 Breakthrough Systems
                                     38
Cause: Common –vs- special
Special Cause Variation:
  If a statistically significant trend occurs, find the
  special cause of this trend. Use this information
  to correct or reinforce these special causes.

Common Cause Variation:
  If no trends exist, you must look at the long run
  performance of the process and fundamentally
  change the process in order to improve the
  process.


                  © 2007 Breakthrough Systems
                                           39
Defining Trending in Charting
• One point outside the control limits
• Two out of Three points two standard deviations
  above/below average
• Four out of Five points one standard deviation
  above/below average
• Seven points in a row all above/below average
• Ten out of Eleven points in a row all above/below
  average
• Seven points in a row all increasing/decreasing



                © 2007 Breakthrough Systems
                                         40
Trending Example on
    Control Chart




    © 2007 Breakthrough Systems
                             41
Constructing a Control Chart

• Plot the actual data by month (or
  whatever time interval you are using)
• Plot at least 25 points (when available)
• Calculate a baseline average rate
• Add 3 standard deviation control limits
• Incorporate a set of trend rules


              © 2007 Breakthrough Systems
                                       42
Why 3 Standard Deviations?
• Dr. Shewhart established 3 standard
  deviations as an economic balance
  between failure to detect and false
  alarms.
• Economic Control of Quality of
  Manufactured Product (1931!)



             © 2007 Breakthrough Systems
                                      43
Just in Case…
• Many courses incorrectly teach that the
  control limits cover 99.7% of the normal
  distribution
• Not all data are normal, “real data” can cause
  the rate to be as low as 95% (Dr. Wheeler)
• The Tchebychev Inequality states up to 11%
  can be outside three standard deviations


               © 2007 Breakthrough Systems
                                        44
Breather – We OK?
• stable –vs- unstable
• common –vs- special
• constructing a control chart
     (or a process behavior chart)
• 3 Standard Deviation limits



             © 2007 Breakthrough Systems
                                      45
Choosing Performance
     Indicators




     © 2007 Breakthrough Systems
                              46
Group Activity – VI
• As individuals, take your SIPOC & 4M
  exercise, and
  – Identify a performance indicator on the input and
    then the output of the process you have
    diagrammed and explain why you chose it
  – Share and discuss your choice with your team
  – Choose 2 or 3 examples from the team to share
    with the class
  – Remember: you are hunting red beads


                © 2007 Breakthrough Systems
                                         47
Activity Debrief
• What indicators did you choose?
• Why?
• What actions would you take if one
  developed an adverse trend?




             © 2007 Breakthrough Systems
                                      48
Choosing the Right Measures

“Managers who don’t know how to
measure what they want settle for
wanting what they can measure.”

Dr. Russ Ackoff



          © 2007 Breakthrough Systems
                                   49
Performance Indicator
           Introduction
• It is more important how the measure is
  used than what the measure is
• Self-fulfilling prophecies can prevent us
  from gathering any data
• We are drowning in data, but little
  knowledge is derived
• Context and Operational Definitions are
  crucial

              © 2007 Breakthrough Systems
                                       50
5 Critical Issues ( 1-3)
• Managers suffer from overabundance
  of irrelevant information.
• Managers don’t know what information
  they need. Need to look at the decision
  process to determine this.
• Even if given the information they need,
  decision making will not necessarily
  improve

             © 2007 Breakthrough Systems
                                      51
5 Critical Issues (4-5)
• More communication does not
  necessarily lead to better performance.
  Information can be used destructively.
• Managers do need to know how the
  information system works. Just
  because it came from a computer
  doesn’t mean it is right.

             © 2007 Breakthrough Systems
                                      52
Designing a Management
          System
• The information system should be
  designed as an integral part of the
  management system
• Most information systems are designed
  independently, leading to failure
• Information systems should serve
  management, not vice versa

            © 2007 Breakthrough Systems
                                     53
PI Barriers
• higher ups will use it as a “hammer”
• subjected to quotas and targets imposed from
  above
• fear (“accountability”) used as a “motivator”
• actions and explanations as a result of
  random fluctuations
• perceived loss of control over portrayal of
  performance
• must develop “perfect” indicator the first time
• use of SPC can minimize these fears

               © 2007 Breakthrough Systems
                                        54
Ackoff on Performance
          Indicators
• We do need to know the context within
  which the performance indicators will be
  used
• Forecasting and living with the
  forecasted future is important, but what
  about designing a better future?



             © 2007 Breakthrough Systems
                                      55
Context of PI
• Do not look at a chart in a vacuum
• Reconcile any differences between the
  data and “gut feeling”
• Combine experience and the data
• Lessons from the data should lead to
  insight in the field, and vice versa


            © 2007 Breakthrough Systems
                                     56
PI Evolution
As a process matures, one may end up evolving the
  indicators used. For example, if interested in
  completing actions by commitment dates, one
  may end up using (as the process matures):

     • Percent of Actions completed by due date in effect at
       time of completion
     • Percent of Actions completed without missing any
       due dates during their life
     • Percent of Actions completed by the original due
       date
     • Average days Actions completed ahead of original
       due date


                 © 2007 Breakthrough Systems
                                          57
Trying for the “Perfect” PI
• When committees get together and try to table-top
  the perfect indicator, paralysis often sets in.
• Realize all data are flawed, there is no “true value”,
  indicators can always be “gamed.”
• Putting the right culture of HOW to use performance
  indicators in place minimizes adverse impacts.
• Gain experience with simple indicators, then move on
  to more complex indicators if needed.
• With proper analysis, flaws with existing data can be
  detected and fixed. If you never look at the data,
  there will never be an incentive to fix the data.

                  © 2007 Breakthrough Systems
                                           58
Just Do It!
• All data are flawed
• Make good use of your data
• Endless conference table
  discussions won’t cause any data
  to appear
• Initial prototype successes will lead
  to experience, and will further the
  spread of the use of indicators
            © 2007 Breakthrough Systems
                                     59
Data Gathering
•   Plan ahead
•   Establish Operational Definitions
•   Check data quality
•   Avoid bias
•   K.I.S.S.



               © 2007 Breakthrough Systems
                                        60
Data Quality
• Data should be replicable
• Operational Definitions are a must
• Source Data must be defined
• There is no “true value” of any measure, but a
  good operational definition can save much
  trouble in the future
• ANYONE at ANYTIME in the future should be
  able to apply the same operational definition
  to the same source data, and get the same
  results.

               © 2007 Breakthrough Systems
                                        61
Choose a Reporting Interval
• If a trend developed, how long could
  you go without needing to know it?
• Longer intervals imply more risk
• Need sufficient volume of points (25)
• Costs increase as reporting interval
  decreases
• What is current reporting interval?

             © 2007 Breakthrough Systems
                                      62
Creating a Control Chart




      © 2007 Breakthrough Systems
                               63
Creating the Baseline
• The Baseline on a control chart consists
  of the average (center) line, a three-
  standard deviation Upper Control Limit
  (UCL) and a three-standard deviation
  Lower Control Limit (LCL).
• The Baseline allows us to predict the
  future, and evaluate for trends.

             © 2007 Breakthrough Systems
                                      64
A Good Baseline
• A “good” baseline detects future trends
  with a minimum of false alarms.
• If a trend is detected, we don’t want it to
  be due to too few data points in the
  baseline, causing the baseline to have
  been inaccurate.



              © 2007 Breakthrough Systems
                                       65
To get a Good Baseline
Do show all data, but change the average
  and control limit calculations by:
• Dropping data off of the beginning
• Dropping data off of the end
• Dropping individual datum point(s) and
  circling them


            © 2007 Breakthrough Systems
                                     66
Dropping 1st 3 Points




     © 2007 Breakthrough Systems
                              67
Establish Expectations
• “Stable” performance is not necessarily
  good
• Management needs to determine if the
  current stable baseline is “acceptable”
  or “unacceptable”
• Recall that the # of red beads was
  unacceptable, but process was stable
  and in control

             © 2007 Breakthrough Systems
                                      68
Monitoring
• Update charts on the required time interval
• Check for trends against the trending rules
• Circle any trends, inform owning
  management and look for special cause(s)
• Do not shift a baseline unless there is a trend
  (baseline proven guilty)




                © 2007 Breakthrough Systems
                                         69
That’s Charting Performance
    Indicators in a Nutshell
• PI as part of an overall management
  system
• What makes a good performance
  indicator
• Data gathering
• Establishing a good baseline
• Establishing Expectations
• Monitoring
             © 2007 Breakthrough Systems
                                      70
Review Control Chart of Red
     Bead Experiment




       © 2007 Breakthrough Systems
                                71
Session Summary
   The Red Bead Experiment
   Numeracy
   System of Profound Knowledge
   Finding Red beads
   Impact of psychology
   Charting red beads
   “What will you do on Monday?”
             © 2007 Breakthrough Systems
                                      72
What will you do on Monday?

• Well???




            © 2007 Breakthrough Systems
                                     73
Questions?




© 2007 Breakthrough Systems
                         74
Wrap & Roll…
Thanks for your time and attention

            Jim Clauson
        jim@jclauson.com
     http://jclauson.com/aice



          © 2007 Breakthrough Systems
                                   75

Contenu connexe

Tendances

Systemsthinking 12632353422762 Phpapp01
Systemsthinking 12632353422762 Phpapp01Systemsthinking 12632353422762 Phpapp01
Systemsthinking 12632353422762 Phpapp01Myra Frazier
 
Root cause analysis
Root cause analysisRoot cause analysis
Root cause analysisSimmy Sharma
 
Systems Thinking and Unthinkable Thoughts
Systems Thinking and Unthinkable ThoughtsSystems Thinking and Unthinkable Thoughts
Systems Thinking and Unthinkable ThoughtsJoel Eden, PhD
 
Why Your Agile Rollout Is Failing
Why Your Agile Rollout Is FailingWhy Your Agile Rollout Is Failing
Why Your Agile Rollout Is FailingDan North
 
Getting things done mid submission
Getting things done mid submissionGetting things done mid submission
Getting things done mid submissionSameer Mathur
 
Troubleshooting The Troubleshootingsystem Kl480
Troubleshooting The Troubleshootingsystem Kl480Troubleshooting The Troubleshootingsystem Kl480
Troubleshooting The Troubleshootingsystem Kl480Jens Refflinghaus
 
Introduction to Systems Thinking
Introduction to Systems ThinkingIntroduction to Systems Thinking
Introduction to Systems ThinkingAnupam Saraph
 
Kerry.mushkin
Kerry.mushkinKerry.mushkin
Kerry.mushkinNASAPMC
 
Fostering innovation in mature enterprises
Fostering innovation in mature enterprisesFostering innovation in mature enterprises
Fostering innovation in mature enterprisesDave Litwiller
 
Theory of constraints._eliyahu_m._goldra
Theory of constraints._eliyahu_m._goldraTheory of constraints._eliyahu_m._goldra
Theory of constraints._eliyahu_m._goldraJuan Colin
 
Introduction to TRIZ(TIPS)
Introduction to TRIZ(TIPS)Introduction to TRIZ(TIPS)
Introduction to TRIZ(TIPS)Kavya Mithran
 
Worthwhile Technology Foundations
Worthwhile Technology FoundationsWorthwhile Technology Foundations
Worthwhile Technology FoundationsWill Koffel
 
Brighttalk getting back on track - final
Brighttalk   getting back on track - finalBrighttalk   getting back on track - final
Brighttalk getting back on track - finalAndrew White
 
smAlbany 2013 gn bdr pp
smAlbany 2013 gn bdr ppsmAlbany 2013 gn bdr pp
smAlbany 2013 gn bdr ppLiberteks
 
Brighttalk learning to cook- network management recipes - final
Brighttalk   learning to cook- network management recipes - finalBrighttalk   learning to cook- network management recipes - final
Brighttalk learning to cook- network management recipes - finalAndrew White
 
Lean Principles Everyone Should Use (Final)
Lean Principles Everyone Should Use (Final)Lean Principles Everyone Should Use (Final)
Lean Principles Everyone Should Use (Final)Todd Mills
 

Tendances (20)

Systemsthinking 12632353422762 Phpapp01
Systemsthinking 12632353422762 Phpapp01Systemsthinking 12632353422762 Phpapp01
Systemsthinking 12632353422762 Phpapp01
 
Root cause analysis
Root cause analysisRoot cause analysis
Root cause analysis
 
Systems Thinking and Unthinkable Thoughts
Systems Thinking and Unthinkable ThoughtsSystems Thinking and Unthinkable Thoughts
Systems Thinking and Unthinkable Thoughts
 
More with LeSS
More with LeSSMore with LeSS
More with LeSS
 
Why Your Agile Rollout Is Failing
Why Your Agile Rollout Is FailingWhy Your Agile Rollout Is Failing
Why Your Agile Rollout Is Failing
 
Getting things done mid submission
Getting things done mid submissionGetting things done mid submission
Getting things done mid submission
 
Troubleshooting The Troubleshootingsystem Kl480
Troubleshooting The Troubleshootingsystem Kl480Troubleshooting The Troubleshootingsystem Kl480
Troubleshooting The Troubleshootingsystem Kl480
 
Elder
ElderElder
Elder
 
Introduction to Systems Thinking
Introduction to Systems ThinkingIntroduction to Systems Thinking
Introduction to Systems Thinking
 
Kerry.mushkin
Kerry.mushkinKerry.mushkin
Kerry.mushkin
 
Fostering innovation in mature enterprises
Fostering innovation in mature enterprisesFostering innovation in mature enterprises
Fostering innovation in mature enterprises
 
Assign8
Assign8Assign8
Assign8
 
Theory of constraints._eliyahu_m._goldra
Theory of constraints._eliyahu_m._goldraTheory of constraints._eliyahu_m._goldra
Theory of constraints._eliyahu_m._goldra
 
Introduction to TRIZ(TIPS)
Introduction to TRIZ(TIPS)Introduction to TRIZ(TIPS)
Introduction to TRIZ(TIPS)
 
Worthwhile Technology Foundations
Worthwhile Technology FoundationsWorthwhile Technology Foundations
Worthwhile Technology Foundations
 
Brighttalk getting back on track - final
Brighttalk   getting back on track - finalBrighttalk   getting back on track - final
Brighttalk getting back on track - final
 
smAlbany 2013 gn bdr pp
smAlbany 2013 gn bdr ppsmAlbany 2013 gn bdr pp
smAlbany 2013 gn bdr pp
 
About the marvels and the flaws of intuitive thinking
About the marvels and the flaws of intuitive thinkingAbout the marvels and the flaws of intuitive thinking
About the marvels and the flaws of intuitive thinking
 
Brighttalk learning to cook- network management recipes - final
Brighttalk   learning to cook- network management recipes - finalBrighttalk   learning to cook- network management recipes - final
Brighttalk learning to cook- network management recipes - final
 
Lean Principles Everyone Should Use (Final)
Lean Principles Everyone Should Use (Final)Lean Principles Everyone Should Use (Final)
Lean Principles Everyone Should Use (Final)
 

En vedette

En vedette (7)

2010 08-25 svenska stadskärnor jeanette berggren
2010 08-25 svenska stadskärnor jeanette berggren2010 08-25 svenska stadskärnor jeanette berggren
2010 08-25 svenska stadskärnor jeanette berggren
 
Språk
SpråkSpråk
Språk
 
Du kodar väl på svenska?
Du kodar väl på svenska?Du kodar väl på svenska?
Du kodar väl på svenska?
 
From Scrum To Kanban
From Scrum To KanbanFrom Scrum To Kanban
From Scrum To Kanban
 
Svenska
SvenskaSvenska
Svenska
 
Sv Presentation
Sv PresentationSv Presentation
Sv Presentation
 
Red Beads Experiment
Red Beads ExperimentRed Beads Experiment
Red Beads Experiment
 

Similaire à Aice mar07 deming_workshop_master

Understanding the impact of certain uncertain event using bayesian network
Understanding the impact of  certain uncertain event using bayesian networkUnderstanding the impact of  certain uncertain event using bayesian network
Understanding the impact of certain uncertain event using bayesian networkKobi Vider
 
Management Ch 6. PPT.pptx
Management Ch 6. PPT.pptxManagement Ch 6. PPT.pptx
Management Ch 6. PPT.pptxNovalonPolymers
 
Living in a fantasy world – theoretical system implementations
Living in a fantasy world – theoretical system implementationsLiving in a fantasy world – theoretical system implementations
Living in a fantasy world – theoretical system implementationsJohn Cachat
 
Robbins9 ppt06
Robbins9 ppt06Robbins9 ppt06
Robbins9 ppt06umar0007
 
Problem solving & decision making
Problem solving & decision makingProblem solving & decision making
Problem solving & decision makingSoft Skills World
 
Managerial Decision-Making
Managerial Decision-MakingManagerial Decision-Making
Managerial Decision-MakingLee Schlenker
 
Chapter6decisionmakingtheessenceofthemanagersjobppt06 100223215436-phpapp01
Chapter6decisionmakingtheessenceofthemanagersjobppt06 100223215436-phpapp01Chapter6decisionmakingtheessenceofthemanagersjobppt06 100223215436-phpapp01
Chapter6decisionmakingtheessenceofthemanagersjobppt06 100223215436-phpapp01sheetslibrary
 
Technologies and Innovation – Decision Making
Technologies and Innovation – Decision MakingTechnologies and Innovation – Decision Making
Technologies and Innovation – Decision MakingLee Schlenker
 
8d training slides
8d training slides 8d training slides
8d training slides Rohit Singh
 
Engineering Perspectives on Business
Engineering Perspectives on Business Engineering Perspectives on Business
Engineering Perspectives on Business Michael Zargham
 
Comparing Two Types of Decision-making: When experts are better -- or not
Comparing Two Types of Decision-making: When experts are better -- or notComparing Two Types of Decision-making: When experts are better -- or not
Comparing Two Types of Decision-making: When experts are better -- or notKerry Cunningham
 
Big Data LDN 2017: Preserving The Key Principles Of Academic Research In A Bu...
Big Data LDN 2017: Preserving The Key Principles Of Academic Research In A Bu...Big Data LDN 2017: Preserving The Key Principles Of Academic Research In A Bu...
Big Data LDN 2017: Preserving The Key Principles Of Academic Research In A Bu...Matt Stubbs
 

Similaire à Aice mar07 deming_workshop_master (20)

Understanding the impact of certain uncertain event using bayesian network
Understanding the impact of  certain uncertain event using bayesian networkUnderstanding the impact of  certain uncertain event using bayesian network
Understanding the impact of certain uncertain event using bayesian network
 
Iti week 10 (3)
Iti week 10 (3)Iti week 10 (3)
Iti week 10 (3)
 
Chap06
Chap06Chap06
Chap06
 
Management Ch 6. PPT.pptx
Management Ch 6. PPT.pptxManagement Ch 6. PPT.pptx
Management Ch 6. PPT.pptx
 
Living in a fantasy world – theoretical system implementations
Living in a fantasy world – theoretical system implementationsLiving in a fantasy world – theoretical system implementations
Living in a fantasy world – theoretical system implementations
 
Robbins9 ppt06
Robbins9 ppt06Robbins9 ppt06
Robbins9 ppt06
 
Robbins9 ppt06
Robbins9 ppt06Robbins9 ppt06
Robbins9 ppt06
 
Problem solving & decision making
Problem solving & decision makingProblem solving & decision making
Problem solving & decision making
 
Managerial Decision-Making
Managerial Decision-MakingManagerial Decision-Making
Managerial Decision-Making
 
Unleashing the Creative Potential of Your Teams
Unleashing the Creative Potential of Your TeamsUnleashing the Creative Potential of Your Teams
Unleashing the Creative Potential of Your Teams
 
Chapter6decisionmakingtheessenceofthemanagersjobppt06 100223215436-phpapp01
Chapter6decisionmakingtheessenceofthemanagersjobppt06 100223215436-phpapp01Chapter6decisionmakingtheessenceofthemanagersjobppt06 100223215436-phpapp01
Chapter6decisionmakingtheessenceofthemanagersjobppt06 100223215436-phpapp01
 
Technologies and Innovation – Decision Making
Technologies and Innovation – Decision MakingTechnologies and Innovation – Decision Making
Technologies and Innovation – Decision Making
 
8d training slides
8d training slides 8d training slides
8d training slides
 
Root Cause Analysis
Root Cause AnalysisRoot Cause Analysis
Root Cause Analysis
 
Engineering Perspectives on Business
Engineering Perspectives on Business Engineering Perspectives on Business
Engineering Perspectives on Business
 
Management Decision Making
Management Decision MakingManagement Decision Making
Management Decision Making
 
Ch 6-Slides
Ch 6-SlidesCh 6-Slides
Ch 6-Slides
 
Data science
Data scienceData science
Data science
 
Comparing Two Types of Decision-making: When experts are better -- or not
Comparing Two Types of Decision-making: When experts are better -- or notComparing Two Types of Decision-making: When experts are better -- or not
Comparing Two Types of Decision-making: When experts are better -- or not
 
Big Data LDN 2017: Preserving The Key Principles Of Academic Research In A Bu...
Big Data LDN 2017: Preserving The Key Principles Of Academic Research In A Bu...Big Data LDN 2017: Preserving The Key Principles Of Academic Research In A Bu...
Big Data LDN 2017: Preserving The Key Principles Of Academic Research In A Bu...
 

Dernier

Oι πιο ευτυχισμένες και οι πιο δυστυχισμένες χώρες: Πρωτιά για τη Φινλανδία -...
Oι πιο ευτυχισμένες και οι πιο δυστυχισμένες χώρες: Πρωτιά για τη Φινλανδία -...Oι πιο ευτυχισμένες και οι πιο δυστυχισμένες χώρες: Πρωτιά για τη Φινλανδία -...
Oι πιο ευτυχισμένες και οι πιο δυστυχισμένες χώρες: Πρωτιά για τη Φινλανδία -...Newsroom8
 
Beyond Academics - Anibal Romero .pdf
Beyond Academics - Anibal Romero    .pdfBeyond Academics - Anibal Romero    .pdf
Beyond Academics - Anibal Romero .pdfroberttianibal
 
The Heirloom Gown: A Tale of Love and Legacy
The Heirloom Gown: A Tale of Love and LegacyThe Heirloom Gown: A Tale of Love and Legacy
The Heirloom Gown: A Tale of Love and Legacyirumsohale
 
Secrets for A Happy Relationship & Marriage.
Secrets for A Happy Relationship & Marriage.Secrets for A Happy Relationship & Marriage.
Secrets for A Happy Relationship & Marriage.Surajkurrey
 
HVAC Replacement Process for Commercial Buildings Guide
HVAC Replacement Process for Commercial Buildings GuideHVAC Replacement Process for Commercial Buildings Guide
HVAC Replacement Process for Commercial Buildings Guideoutreachacdirect
 
Bridging Cultures: Antique Indian Doors with Mediterranean Arches
Bridging Cultures: Antique Indian Doors with Mediterranean ArchesBridging Cultures: Antique Indian Doors with Mediterranean Arches
Bridging Cultures: Antique Indian Doors with Mediterranean ArchesEra Chandok
 
Boys Wholesale Clothing Online | Port 213
Boys Wholesale Clothing Online | Port 213Boys Wholesale Clothing Online | Port 213
Boys Wholesale Clothing Online | Port 213Port 213
 
Alex Gurkin: Strategies for a Sustainable Tech Career
Alex Gurkin: Strategies for a Sustainable Tech CareerAlex Gurkin: Strategies for a Sustainable Tech Career
Alex Gurkin: Strategies for a Sustainable Tech CareerAlex Gurkin
 

Dernier (8)

Oι πιο ευτυχισμένες και οι πιο δυστυχισμένες χώρες: Πρωτιά για τη Φινλανδία -...
Oι πιο ευτυχισμένες και οι πιο δυστυχισμένες χώρες: Πρωτιά για τη Φινλανδία -...Oι πιο ευτυχισμένες και οι πιο δυστυχισμένες χώρες: Πρωτιά για τη Φινλανδία -...
Oι πιο ευτυχισμένες και οι πιο δυστυχισμένες χώρες: Πρωτιά για τη Φινλανδία -...
 
Beyond Academics - Anibal Romero .pdf
Beyond Academics - Anibal Romero    .pdfBeyond Academics - Anibal Romero    .pdf
Beyond Academics - Anibal Romero .pdf
 
The Heirloom Gown: A Tale of Love and Legacy
The Heirloom Gown: A Tale of Love and LegacyThe Heirloom Gown: A Tale of Love and Legacy
The Heirloom Gown: A Tale of Love and Legacy
 
Secrets for A Happy Relationship & Marriage.
Secrets for A Happy Relationship & Marriage.Secrets for A Happy Relationship & Marriage.
Secrets for A Happy Relationship & Marriage.
 
HVAC Replacement Process for Commercial Buildings Guide
HVAC Replacement Process for Commercial Buildings GuideHVAC Replacement Process for Commercial Buildings Guide
HVAC Replacement Process for Commercial Buildings Guide
 
Bridging Cultures: Antique Indian Doors with Mediterranean Arches
Bridging Cultures: Antique Indian Doors with Mediterranean ArchesBridging Cultures: Antique Indian Doors with Mediterranean Arches
Bridging Cultures: Antique Indian Doors with Mediterranean Arches
 
Boys Wholesale Clothing Online | Port 213
Boys Wholesale Clothing Online | Port 213Boys Wholesale Clothing Online | Port 213
Boys Wholesale Clothing Online | Port 213
 
Alex Gurkin: Strategies for a Sustainable Tech Career
Alex Gurkin: Strategies for a Sustainable Tech CareerAlex Gurkin: Strategies for a Sustainable Tech Career
Alex Gurkin: Strategies for a Sustainable Tech Career
 

Aice mar07 deming_workshop_master

  • 1. Deming’s Red Bead Experiment AICE Quality Conference Tuesday, 06MAR07 Jim Clauson Breakthrough Systems http://jclauson.com/aice © 2007 Breakthrough Systems 1
  • 2. Why Are We Here? To consider: • what the Red Bead Experiment is, • what it has to do with quality and • how it can have an impact on your everyday quality activities © 2007 Breakthrough Systems 2
  • 3. Session Agenda  The Red Bead Experiment  Numeracy  System of Profound Knowledge  Finding Red beads  Impact of psychology  Charting red beads  “What will you do on Monday?” © 2007 Breakthrough Systems 3
  • 4. Introductions and Expectations • If you are sitting with someone you know, please move • You will interview, then introduce the person next to you • Who they are, something unique or interesting, what industry they represent, and what their expectations are today © 2007 Breakthrough Systems 4
  • 5. Run Red Bead Experiment • Click [here] for the red bead slides. © 2007 Breakthrough Systems 5
  • 6. Review: Why Are We Here? To consider: • what the Red Bead Experiment is, • what it has to do with quality and • how it can have an impact on your everyday quality activities © 2007 Breakthrough Systems 6
  • 7. Beyond Red Beads • Red Beads Everywhere, oh my!! • Finding those red beads – Red, white and non-red? • Quantifying those read beads – Hit by a car –vs- bump a file cabinet • Eliminating those red beads – 99.99999999999999999999999999% © 2007 Breakthrough Systems 7
  • 8. Numeracy • an ability to handle numbers and other mathematical concepts • in the US, it is somewhat better known as Quantitative Literacy • innumeracy is a lack of numeracy © 2007 Breakthrough Systems 8
  • 9. 3 Kinds of Numbers for Management. • Facts of life. If we don't make this profit figure, we will go out of business. • Planning, prediction and budget. Can be used to compare alternative plans. • Arbitrary numerical targets. Generally used to judge workers. Avoid the use of the 3rd kind of number Henry Neave The Deming Dimension © 2007 Breakthrough Systems 9
  • 10. Data Sanity We can either react to numbers, with explanations of every percent change, with the inherent frustrations, fear, and failure Or We can understand our data, put it to good use, and apply valid management principles The choice is ours. © 2007 Breakthrough Systems 10
  • 11. Through the Lens of SoPK System of Profound Knowledge • Appreciation for a system • Knowledge about variation • Theory of Knowledge • Psychology From The New Economics, Deming © 2007 Breakthrough Systems 11
  • 12. 1 of 4: Appreciation for a System • Pay attention to interactions more so than components • Knowledge of statistical variation more so than discrete numbers • Long term focus more so than short term • Cooperation more so than fear, blame and internal competition © 2007 Breakthrough Systems 12
  • 13. 1 of 4: Appreciation for a System - II • “94% of the outcome of any organization comes from the processes used, not the people”. • “A fault in the interpretation of observations, seen everywhere, is to suppose that every event is attributable to someone (usually the one closest at hand), or is related to some special event. The fact is that most troubles with service and production lie in the system and not the people”. © 2007 Breakthrough Systems 13
  • 14. 2 of 4: Knowledge of Variation • You have experienced the Red Bead Experiment • The Theory of Variation is at the core of cost savings, Kaizen, 6 sigma… • Dr. Deming’s early works focused on statistical variation. He added the rest of the SOPK in the last 10 years of his life. • Stable System versus Unstable System © 2007 Breakthrough Systems 14
  • 15. Variation: Deterministic –vs- Probabilistic • Deterministic - linear, cause and effect sequences. If you do this, that will happen. • Probabilistic - exact time, location, and effect is random. e.g. Number of Red Beads. • Treating a probabilistic result as if it was deterministic will cause problems • Past results will not guarantee future results © 2007 Breakthrough Systems 15
  • 16. Variation: Can we predict? • Engineers often predict accidents. Their predictions are uncanny for correctness in detail. They fail in only one way – they can not predict exactly when the accident will happen. - Dr. Deming, Out of the Crisis page 479 • Calculations after the fact, using only data available prior to the disaster, showed there was greater than a 10% chance of the Challenger explosion occurring, given the pre-launch temperatures and prior history of O-ring burn through. © 2007 Breakthrough Systems 16
  • 17. 3 of 4: Theory of Knowledge - I • Knowledge is based upon prediction • Knowledge is built on theory – Chanticleer the barnyard rooster – Actions taken without theory lead to losses • Use of data requires prediction • There is no true value of a measurement, it depends on methods, context, and use • Operational definitions are necessary © 2007 Breakthrough Systems 17
  • 18. Operational Definitions - I • “Clean the table… © 2007 Breakthrough Systems 18
  • 19. Operational Definitions - II • Most arguments about conflicting data come down to the definition of how to count the data • Try to be precise in your definitions, but likely something unforeseen will arise • The beads were: – red & white or red, white & non-red? © 2007 Breakthrough Systems 19
  • 20. Deming said… • “It’s absolutely vital for business that you settle this method of counting, measuring, definition of faults, mistake, defect, before you do business. It’s too late afterwards” -Dr. W. Edwards Deming © 2007 Breakthrough Systems 20
  • 21. 4 of 4: Psychology • Extrinsic versus intrinsic motivation • People will use the charts you make - up and down the organization • If you do not understand the people & understand psychology, the charts will be ignored • Competition, fear, perceptions, loss of control change the data and the chart’s message © 2007 Breakthrough Systems 21
  • 22. Through the Lens of SoPK System of Profound Knowledge • Appreciation for a system • Knowledge about variation • Theory of Knowledge • Psychology • Thinking about all 4, we’ll concentrate on identifying and quantifying variation © 2007 Breakthrough Systems 22
  • 23. Red Beads: Find, Quantify, Reduce © 2007 Breakthrough Systems 23
  • 24. Take a Step Back: Systems Thinking • Process viewed as a system • SIPOC • The “new” 4M’s • Psychology: Suboptimization • Remember the “94/6 Rule” • Using SPC © 2007 Breakthrough Systems 24
  • 25. Production Viewed as a System © 2007 Breakthrough Systems 25
  • 26. SIPOC • Supplier • Input • Process • Output • Customer © 2007 Breakthrough Systems 26
  • 27. The “new” 4M’s • Old: man, machine, material, method • Measurement added • Person or people replaces man • Equipment replaces machine • Supplies is used for material • Process is used for method • Environment added – Physical and mental © 2007 Breakthrough Systems 27
  • 28. Group Activity - IV • As individuals, draw a SIPOC diagram for your job • See if you can identify all of the new 4M’s as inputs to your process • Compare and discuss as teams • Choose the 3 most interesting to report • Save this work, it will be used later © 2007 Breakthrough Systems 28
  • 29. Psychology: Suboptimization • We assume that optimizing a system considers all the sub-parts • One unit may be selfish and take an action that makes them look good, but hurts others • One process may shift problems down the line to let others have to worry about it © 2007 Breakthrough Systems 29
  • 30. No Gold Stars Here • Awards, bonuses, gold stars can actually have a detrimental impact • For a person driven extrinsically, each subsequent reward must be larger in order to have the same impact • Creation of winners and losers http://www.alfiekohn.org/index.html © 2007 Breakthrough Systems 30
  • 31. Group Activity - V Game: Win As Much As You Can A Decision Making Exercise, Illustrating the Effects of Human Behaviors and Psychology on Performance Measures [link] to game © 2007 Breakthrough Systems 31
  • 32. The “94/6%” Rule • It is critical to separate system causes from individual causes of variation • Deming started at 85% systems and 15% worker and had moved up to 96% and 4% by his death • What are the implications of the 96/4% Rule? © 2007 Breakthrough Systems 32
  • 33. Breather – We OK? • What have we addressed? • Numeracy • System of Profound Knowledge • Looking at your work as a system • Suboptimization exercise • 96/4% Rule • We OK? © 2007 Breakthrough Systems 33
  • 34. Statistical Process Control • Control Charting provides knowledge of variation • a lens, providing a different way of viewing the world • a significantly different view of what is happening than will other methods © 2007 Breakthrough Systems 34
  • 35. A Basic Control Chart Injuries per Month - as a Control Chart 25 20 15 10 5 0 May-04 May-05 May-03 Mar-03 Nov-03 Mar-04 Nov-04 Mar-05 Jan-03 Jul-03 Jul-04 Jan-05 Jan-04 Sep-03 Sep-04 © 2007 Breakthrough Systems 35
  • 36. SPC Basics • Common -vs- special • System in control? • System predictable? • What about psychology? © 2007 Breakthrough Systems 36
  • 37. Charting the Red Beads • In the Red Bead Experiment, we reacted to the random noise from result to result. • Rewards, punishments, ranking of the workers, feedback to the workers had no effect on the results of the process. • The process was stable and needed to be changed! © 2007 Breakthrough Systems 37
  • 38. Stable –vs- Unstable • Stable processes contain only common cause variations and are predictable • Unstable processes contain special cause variations and are not predictable. • Only predictable processes may be used to plan effectively © 2007 Breakthrough Systems 38
  • 39. Cause: Common –vs- special Special Cause Variation: If a statistically significant trend occurs, find the special cause of this trend. Use this information to correct or reinforce these special causes. Common Cause Variation: If no trends exist, you must look at the long run performance of the process and fundamentally change the process in order to improve the process. © 2007 Breakthrough Systems 39
  • 40. Defining Trending in Charting • One point outside the control limits • Two out of Three points two standard deviations above/below average • Four out of Five points one standard deviation above/below average • Seven points in a row all above/below average • Ten out of Eleven points in a row all above/below average • Seven points in a row all increasing/decreasing © 2007 Breakthrough Systems 40
  • 41. Trending Example on Control Chart © 2007 Breakthrough Systems 41
  • 42. Constructing a Control Chart • Plot the actual data by month (or whatever time interval you are using) • Plot at least 25 points (when available) • Calculate a baseline average rate • Add 3 standard deviation control limits • Incorporate a set of trend rules © 2007 Breakthrough Systems 42
  • 43. Why 3 Standard Deviations? • Dr. Shewhart established 3 standard deviations as an economic balance between failure to detect and false alarms. • Economic Control of Quality of Manufactured Product (1931!) © 2007 Breakthrough Systems 43
  • 44. Just in Case… • Many courses incorrectly teach that the control limits cover 99.7% of the normal distribution • Not all data are normal, “real data” can cause the rate to be as low as 95% (Dr. Wheeler) • The Tchebychev Inequality states up to 11% can be outside three standard deviations © 2007 Breakthrough Systems 44
  • 45. Breather – We OK? • stable –vs- unstable • common –vs- special • constructing a control chart (or a process behavior chart) • 3 Standard Deviation limits © 2007 Breakthrough Systems 45
  • 46. Choosing Performance Indicators © 2007 Breakthrough Systems 46
  • 47. Group Activity – VI • As individuals, take your SIPOC & 4M exercise, and – Identify a performance indicator on the input and then the output of the process you have diagrammed and explain why you chose it – Share and discuss your choice with your team – Choose 2 or 3 examples from the team to share with the class – Remember: you are hunting red beads © 2007 Breakthrough Systems 47
  • 48. Activity Debrief • What indicators did you choose? • Why? • What actions would you take if one developed an adverse trend? © 2007 Breakthrough Systems 48
  • 49. Choosing the Right Measures “Managers who don’t know how to measure what they want settle for wanting what they can measure.” Dr. Russ Ackoff © 2007 Breakthrough Systems 49
  • 50. Performance Indicator Introduction • It is more important how the measure is used than what the measure is • Self-fulfilling prophecies can prevent us from gathering any data • We are drowning in data, but little knowledge is derived • Context and Operational Definitions are crucial © 2007 Breakthrough Systems 50
  • 51. 5 Critical Issues ( 1-3) • Managers suffer from overabundance of irrelevant information. • Managers don’t know what information they need. Need to look at the decision process to determine this. • Even if given the information they need, decision making will not necessarily improve © 2007 Breakthrough Systems 51
  • 52. 5 Critical Issues (4-5) • More communication does not necessarily lead to better performance. Information can be used destructively. • Managers do need to know how the information system works. Just because it came from a computer doesn’t mean it is right. © 2007 Breakthrough Systems 52
  • 53. Designing a Management System • The information system should be designed as an integral part of the management system • Most information systems are designed independently, leading to failure • Information systems should serve management, not vice versa © 2007 Breakthrough Systems 53
  • 54. PI Barriers • higher ups will use it as a “hammer” • subjected to quotas and targets imposed from above • fear (“accountability”) used as a “motivator” • actions and explanations as a result of random fluctuations • perceived loss of control over portrayal of performance • must develop “perfect” indicator the first time • use of SPC can minimize these fears © 2007 Breakthrough Systems 54
  • 55. Ackoff on Performance Indicators • We do need to know the context within which the performance indicators will be used • Forecasting and living with the forecasted future is important, but what about designing a better future? © 2007 Breakthrough Systems 55
  • 56. Context of PI • Do not look at a chart in a vacuum • Reconcile any differences between the data and “gut feeling” • Combine experience and the data • Lessons from the data should lead to insight in the field, and vice versa © 2007 Breakthrough Systems 56
  • 57. PI Evolution As a process matures, one may end up evolving the indicators used. For example, if interested in completing actions by commitment dates, one may end up using (as the process matures): • Percent of Actions completed by due date in effect at time of completion • Percent of Actions completed without missing any due dates during their life • Percent of Actions completed by the original due date • Average days Actions completed ahead of original due date © 2007 Breakthrough Systems 57
  • 58. Trying for the “Perfect” PI • When committees get together and try to table-top the perfect indicator, paralysis often sets in. • Realize all data are flawed, there is no “true value”, indicators can always be “gamed.” • Putting the right culture of HOW to use performance indicators in place minimizes adverse impacts. • Gain experience with simple indicators, then move on to more complex indicators if needed. • With proper analysis, flaws with existing data can be detected and fixed. If you never look at the data, there will never be an incentive to fix the data. © 2007 Breakthrough Systems 58
  • 59. Just Do It! • All data are flawed • Make good use of your data • Endless conference table discussions won’t cause any data to appear • Initial prototype successes will lead to experience, and will further the spread of the use of indicators © 2007 Breakthrough Systems 59
  • 60. Data Gathering • Plan ahead • Establish Operational Definitions • Check data quality • Avoid bias • K.I.S.S. © 2007 Breakthrough Systems 60
  • 61. Data Quality • Data should be replicable • Operational Definitions are a must • Source Data must be defined • There is no “true value” of any measure, but a good operational definition can save much trouble in the future • ANYONE at ANYTIME in the future should be able to apply the same operational definition to the same source data, and get the same results. © 2007 Breakthrough Systems 61
  • 62. Choose a Reporting Interval • If a trend developed, how long could you go without needing to know it? • Longer intervals imply more risk • Need sufficient volume of points (25) • Costs increase as reporting interval decreases • What is current reporting interval? © 2007 Breakthrough Systems 62
  • 63. Creating a Control Chart © 2007 Breakthrough Systems 63
  • 64. Creating the Baseline • The Baseline on a control chart consists of the average (center) line, a three- standard deviation Upper Control Limit (UCL) and a three-standard deviation Lower Control Limit (LCL). • The Baseline allows us to predict the future, and evaluate for trends. © 2007 Breakthrough Systems 64
  • 65. A Good Baseline • A “good” baseline detects future trends with a minimum of false alarms. • If a trend is detected, we don’t want it to be due to too few data points in the baseline, causing the baseline to have been inaccurate. © 2007 Breakthrough Systems 65
  • 66. To get a Good Baseline Do show all data, but change the average and control limit calculations by: • Dropping data off of the beginning • Dropping data off of the end • Dropping individual datum point(s) and circling them © 2007 Breakthrough Systems 66
  • 67. Dropping 1st 3 Points © 2007 Breakthrough Systems 67
  • 68. Establish Expectations • “Stable” performance is not necessarily good • Management needs to determine if the current stable baseline is “acceptable” or “unacceptable” • Recall that the # of red beads was unacceptable, but process was stable and in control © 2007 Breakthrough Systems 68
  • 69. Monitoring • Update charts on the required time interval • Check for trends against the trending rules • Circle any trends, inform owning management and look for special cause(s) • Do not shift a baseline unless there is a trend (baseline proven guilty) © 2007 Breakthrough Systems 69
  • 70. That’s Charting Performance Indicators in a Nutshell • PI as part of an overall management system • What makes a good performance indicator • Data gathering • Establishing a good baseline • Establishing Expectations • Monitoring © 2007 Breakthrough Systems 70
  • 71. Review Control Chart of Red Bead Experiment © 2007 Breakthrough Systems 71
  • 72. Session Summary  The Red Bead Experiment  Numeracy  System of Profound Knowledge  Finding Red beads  Impact of psychology  Charting red beads  “What will you do on Monday?” © 2007 Breakthrough Systems 72
  • 73. What will you do on Monday? • Well??? © 2007 Breakthrough Systems 73
  • 75. Wrap & Roll… Thanks for your time and attention Jim Clauson jim@jclauson.com http://jclauson.com/aice © 2007 Breakthrough Systems 75