Understanding VariationSlide 2Slide 3Slide 4Slide 5Slide 6Slide 7Reduce Variation - an applied Example Continuous ImprovementUnderstanding Variation“If I had to reduce my message for management to just a few words, I’d say it all had to do with reducing variation.” W. Edwards DemingCommon Causes - Causes of variation that are inherent in the process hour after hour, day after day, and affect every occurrence of the process.Special Causes - Causes that are not in the process all the time or do not affect every occurrence but arise because of special circumstances.Tampering - Reacting to an individual occurrence of a process when only common cause variation is present.CommonSpecialTIMEMEASUREUCLLCLFig. 30. Average weekly scores in golf for a beginner who took lessons before he reached a state of statistical control. Scores for four successive games constituted a sample of size n = 4 for computation of x and R. (The chart for the range is not shown.) Taken from W. Edwards Deming, ELEMENTARY PRINCIPLES OF THE STATISTICAL CONTROL OF QUALITY (Union of Japanese Scientists and Engineers, Tokyo, 1950), p.22. UCL and LCL mean upper control limit and lower control limit.UCLLCLBefore lessons Lessons After lessonsUCLLCLxFig. 32. Average scores in golf for an experienced golfer, before and after lessons. Here the player had already achieved statistical control before he took lessons. The lessons were accordingly ineffective. Scores for four successive games constituted a sample of size n = 4 for computation of x and R. (The chart for the range is not shown.) Taken from W. Edwards Deming, ELEMENTARY PRINCIPLES OF THE STATISTICAL CONTROL OF QUALITY (Union of Japanese Scientists and Engineers, Tokyo, 1950), p. 22.Before lesson LessonsAfter lessonsUpper control limitLower control limitxFig. 31. Average daily scores for a patient learning to walk after an operation: (1) before lessons began; (2) 10 days after lessons began; (3) 3 weeks after lessons began. From Hirokawa and Sugiyama; reference in footnote. The control limits came from the whole group of patients.(1) Just before lessons began.(2) 10 days after lessons began.(3) 3 weeks after lessons began.0.70.80.6xUCLLCLUCLUCLLCLLCLCOMMON CAUSE HIGHWAYSPECIAL CAUSE HIGHWAYManagement Reactions to VariationJ F M A M J J A S O N D J F M A M J J A S OWhat happened???!!!What happened???!!!Good Job!!Good Job!!Good Job!!PerformanceTime PeriodWHY IT DOESN’T PAY TO BE NICEA stable process, one with no indications of a special cause of variation, is said to be, following Shewhart, in statistical control or stable with respect to the quality-characteristics measured. It is a random process. Its behavior in the near future is predictable. Of course, some unforeseen jolt may come along and knock the process out of statistical control. A system that is in statistical control has a definable identity and a definable capability (see: Out of the Crises, p. 339).W. Edwards DemingReduce Variation - an applied ExampleContinuous ImprovementUPPER SPEC LIMITLOWER SPEC LIMITUPPER CONTROL LIMITLOWER CONTROL