2. 6-1 Miller’s Law  “In order to understand what another person is saying, you must assume it is true and try to imagine what it might be true of.” George Miller

3. 6-2 Models of Experts Outpredict the original  Internists diagnosing disease  College admissions committees  Airplane autopilots  Why?

4. 6-3 Why Models Work Better  Explicit Criteria  Consistent application Valid comparisons  Reduce random error  Eliminate irrelevant criteria  Eliminate prejudice based on irrelevant data

5. 6-4 In Business, as in Science  Good Decisions aren’t made---  They follow from the data  Where does the data come from?

6. 6-5  Uses statistics & control charts to identify when to adjust process.  Involves:  Creating standards (upper & lower limits).  Measuring sample output (e.g. mean weight).  Taking corrective action (if necessary).  Done while product is being produced. Statistical Process Control (SPC)

7. 6-6 Outline  Statistical Process Control (SPC).  Mean charts or X -Charts.  Range chart or R -Charts.  Control charts for attributes.  P charts--% defective  C charts—number of defects per piece  Acceptance Sampling.

8. 6-7  Statistical technique to identify when non- random variation is present in a process.  All processes are subject to variability.  Natural causes: Random variations.  Assignable causes: Correctable problems.  Machine wear, unskilled workers, poor materials.  Uses process control charts. Statistical Process Control (SPC)

9. 6-8 Control Charts R Chart Variables Charts Attributes Charts X Chart P C Continuous Numerical Data Categorical or Discrete Numerical Data Control Chart Types

10. 6-9  Characteristics for which you focus on defects.  Categorical or discrete values.  ‘Good’ or ‘Bad’.  # of defects. AttributesVariables Quality Characteristics  Characteristics that you measure, e.g., weight, length.  Continuous values.

11. 6-10 Process Control Charts Plot of Sample Data Over Time 0 20 40 60 80 159131721 Time Sample Value Upper control limit Lower control limit

12. 6-11  Process is not in control if:  Sample is not between upper and lower control limits.  A non-random pattern is present, even when between upper and lower control limits.  Based on sample being normally distributed. Control Charts

13. 6-12  Shows sample means over time.  Monitors process average.  Example: Weigh samples of coffee.  Collect many samples, each of n bags.  Sample size = n.  Compute mean and range for each sample.  Compute upper and lower control limits (UCL, LCL).  Plot sample means and control limits.  X Chart

14. 6-13 Distribution of Sample Means Standard deviation of the sample means (mean)

15. 6-14 As sample size gets large enough, distribution of mean values becomes approximately normal for any population distribution. Central Limit Theorem

16. 6-15  X Chart Control Limits - std. deviation of process is known sample mean at time i  = known process standard deviation

17. 6-16 Each sample is 4 measurements. Process mean is 5 lbs. Process standard deviation is 0.1 lbs. Determine 3σ control limits.  X Chart - Example 1

18. 6-17 Control Chart Patterns

19. 6-18  Shows sample ranges over time.  Sample range = largest - smallest value in sample.  Monitors process variability.  Example: Weigh samples of coffee.  Collect many samples, each of n bags.  Sample size = n.  Compute range for each sample & average range.  Compute upper and lower control limits (UCL, LCL).  Plot sample ranges and control limits. R Chart

20. 6-19  Attributes control chart.  Shows % of nonconforming items.  Example: Count # defective chairs & divide by total chairs inspected.  Chair is either defective or not defective. p Chart

21. 6-20  Attributes control chart.  Shows number of defects in a unit.  Unit may be chair, steel sheet, car, etc.  Size of unit must be constant.  Example: Count # defects (scratches, chips etc.) in each chair of a sample of 100 chairs. c Chart

22. 6-21 Use of Control Charts

23. 6-22  Quality testing for incoming materials or finished goods.  Purchased material & components.  Final products.  Procedure:  Take one or more samples at random from a lot (shipment) of items.  Inspect each of the items in the sample.  Decide whether to reject the whole lot based on the inspection results. Acceptance Sampling

24. 6-23 TQM - Total Quality Management  Encompasses entire organization from supplier to customer.  Commitment by management to a continuing company-wide drive toward excellence in all aspects of products and services that are important to the customer.

25. 6-24 Three Key Figures  W. Edwards Deming  Management & all employees have responsibility for quality.  14 points.  Deming Prize in Japan.  Joseph Juran  Focus on customer.  Continuous improvement and teams.  Philip Crosby  Quality is free!  Cost of poor quality is underestimated.

26. 6-25 Costs of Quality  Internal failure costs.  Scrap and rework.  Downtime.  Safety stock inventory.  Overtime.  External failure costs.  Complaint handling and replacement.  Warranties.  Liability.  Loss of goodwill.

27. 6-26 Why TQM Fails  Lack of commitment by top management  Focusing on specific techniques rather than on the system  Not obtaining employee buy-in and participation  Program stops with training  Expecting immediate results rather than long-term payoff  Forcing the organization to adopt methods that aren't productive or compatible with its production system and personnel  from Martinich, Production and Operations Management

28. 6-27 Customer-focused Quality Management: We treat our employees like dirt and pass the savings on to you.

29. 6-28 Taken in isolation, each step is valid and acceptable... A = B A 2 = AB A 2 - B 2 = AB - B 2 (A + B) (A - B) = (A - B) B (A + B) (A - B) = (A - B) B (A - B) (A - B) (A + B) = B A + A = A 2A = A 2 = 1 But the overall result is absurd.

30. 6-29 Total Quality Management---  Focus on the Long Term best average result rather than immediate short- term outcome.  Emphasize process rather than single result.  Design quality into the process rather than testing defects out of the product.  Aim for zero defects through continuous improvement.  Base vendor decisions on relationship and statistical evidence of quality rather than price.  Buy value rather than price.  Reduce perception of personal risk in decision making.  Drive out fear.  Foster rational laziness.  Let People do the things that are important  and they will seek out the important things to do.

31. 6-30 How Should Business Decisions be Made?  Explicit goals and criteria for success  Consistent best bet decisions  Efficiency with resources  Freedom from Fear  Concern for welfare of the organization  Global view of the organization  People  Geography  Time How ARE Business Decisions Made?

32. 6-31 How Are Business Decisions Made?  Myopia  Personal expediency  Fear of blame  Avoidance of perceived personal risk  Disregard for long term welfare and lack of concern for others.

33. 6-32 Most people are busy--  Being concerned about personal risk  Trying to avoid failure  Afraid of being blamed for occasional misfortunes  Don’t want to take responsibility Some people are too busy--

34. 6-33 Some people are too busy--  Being managers  making “business decisions”  Don’t want to be confused with the data

35. 6-34 The world is filled with--  Soldiers who don’t want to be in the front line  Enthusiastic cross-eyed discus throwers who seldom hit the mark----  but they keep the audience on their toes  Someone has to take the risk and lead:

36. 6-35 Don’t be content to Minimax Regrets  Don’t just play to avoid losing--  Play to win!!  Play so everybody wins.