摩托羅拉六西格瑪企業(yè)培訓(xùn) 2.2 Manage Measurement

1、Additional Department InfoCopyright 2002 Motorola. All rights reserved.Six Sigma Black Belt Program 2.2 Manage Measurement2.2 - 1Six SigmaBlack Belt Program2.2 - ManageMeasurementThese materials, including all attachments, are protected under the copyright laws of the United States and other countri

2、es asan unpublished work. These materials contain information that is proprietary and confidential to Motorola University and are thesubject of a License and Nondisclosure Agreement. Under the terms of the License and Nondisclosure Agreement, thesematerials shall not be disclosed outsider the recipi

3、ents company or duplicated, used or disclosed in whole or in part by therecipient for any purpose other than for the uses described in the License and Nondisclosure Agreement. Any other use ordisclosure of this information, in whole or in part, without the express written permission of Motorola Univ

4、ersity is prohibited.Copyright 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 22.2 Manage MeasurementObjectiveTo establish a discipline and a methodology to be cost-efficient andeffective in collecting data to measure performance.Key Topics Step 1: Develop an Operational Definition S

5、tep 2: Develop a Measurement Plan Step 3: Collect Data Step 4: Display and Evaluate Data2.1DetermineWhat toMeasure2.2ManageMeasurement2.4EvaluateMeasurementSystems2.3EvaluateVariation2.5DetermineProcessPerformanceCopyright 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 3Data Collecti

6、onMeasurement management starts with a data collectionmethodology.Data Collection MethodIdentifyMeasuresStep 1Develop operationaldefinitions for measureStep 2Develop measurement planStep 3Collect dataStep 4Display and evaluate dataAdditional Department InfoCopyright 2002 Motorola. All rights reserve

7、d.Six Sigma Black Belt Program 2.2 Manage Measurement2.2 - 4Step 1.Develop an OperationalDefinitionCopyright 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 5Step 1: Operational DefinitionAn operational definition is a concept that helps guide the teamsthinking on what they need to me

8、asure as well as the key attributes ofthe measure. It provides the foundation for the team to reach agreementand build consistency and reliability into data collection. This helpsensure any person using the agreed-on definition will be measuring thesame thing.Operational DefinitionA precise descript

9、ion of the specific criteria used for the measures. Provides everybody with the same meaning. Ensures that consistency and reliability are built in up front. Describes the scope of the measure (what is included and what is notincluded).“An operational definition puts communicable meaning into aconce

10、pt.” W. Edwards DemingCopyright 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 6Example: Operational Definition Poor: Cycle Time for applications. Good: Collect data from all applications received by fax.The response time will be determined by the dateand time of the fax received (as

11、 shown on the faxedapplication), to the time the approval or rejectionletter is faxed to the applicant (as shown on the faxlog).Copyright 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 7Six Sigma and Operational Definitions Operational definitions enable a team to fully agree on how

12、a particularcharacteristic of a process is to be measured. It is the processcharacteristic that is critical to the satisfaction of the customer. Therefore, when developing an operational definition, it is important forthe team to fully understand and agree that the definition reflects exactlywhat in

13、formation the team is attempting to gather on the process. Clarity is even more important when developing and selecting themeasures that will be used to determine the sigma performance of aprocess. Operational definitions may determine if a team is to count all the defectson an invoice (required to

14、calculate defects per million opportunities) orthe total number of defective invoices (any invoice with any defect) or thetype of defects encountered on an invoice (to eliminate the most commondefects first). Each of these cases may require a very different approachfor gathering the data.Operational

15、 definitions help ensure that the team does it right the firsttime when it comes to data collection.Copyright 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 8Exercise: Operational DefinitionObjectiveTo practice developing an operational definition.Instructions1. Select one of the two

16、 examples below.2. Write an operational definition for each that will be clear to allwho need to understand it.3. Prepare to share the definitions with the class.A. On-Time Departures. A consumer organization wants to rate airlineson how successful they are at meeting the departure schedule as putfo

17、rward by airports. But before the organization can start it needs anoperational definition of when the airplane departs.B. Cycle Time of the Loan Process from Sigma Savings and Loans.Optional Exercise: M & M ExerciseAdditional Department InfoCopyright 2002 Motorola. All rights reserved.Six Sigma Bla

18、ck Belt Program 2.2 Manage Measurement2.2 - 9Step 2.Develop a Measurement PlanCopyright 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 10Step 2: Develop a Measurement Plan Determining current process performance usually requires thecollection of data. When developing a measurement pl

19、an ensure that: The data collected is meaningful. The data collected is valid. All relevant data is collected concurrently. What logistical issues are relevant? Who will collect data? Where is the data located? When will it be collected? What additional assistance is required? What do you want to do

20、 with the data? Use daily, weekly, etc. Identify trends in the process data. Identify deficiencies in the process. Demonstrate current processperformance. Identify variation in a process. Identify a cause and effect relationship.Questions to Answer What precise data will be collected? Performance me

21、asurement? Causes of process deficiencies? Do we analyze all relevant data or a sample? What is the right sample size? What is the right frequency? What will be the sample selectionmethod? What tools are necessary? What formats will be used? What logs will be kept? Do we need a computer?Copyright 20

22、02 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 11Two Basic Types of Data Continuous or variables data - measured on acontinuum or scale. Usually continuous measures canbe divided into parts and still make sense. Forexample: Time can be divided into days, hours, minutes, or seconds(cycl

23、e time). Money can logically be divided or specified in increments(sales, costs, losses). Discrete, categorical, or attribute data. For example: Defects (yes/no, approved/disapproved, pass/fail, metcustomer requirement/did not meet customer requirement). Categories (days of the week, locations, type

24、 of customer, typeof product, risk - low/medium/high). Percent defective.2.2 Manage MeasurementDevelop a Measurement Plan - Types of Data Before data collection starts, classify the data into differenttypes: continuous or discrete. This is important because itwill:Provide a choice of data display an

25、d analysis tools.Dictate sample size calculation.Provide performance or cause information.Determine the appropriate control chart to use.Determine the appropriate method for calculation of 6.ContinuousMeasured on a continuumTimeMoneyWeightLengthDiscreteCategoriesOrdinalCount defects# approved# of er

26、rors2.2 - 12NominalYes/NoCategoriesPercentdefectiveCopyright 2002 Motorola. All rights reserved.Copyright 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 13Performance Data (Y) Performance data are, for the most part, descriptive in nature. Theydescribe process results (your products

27、or services) in terms of time,cost, quantity, and so on. Performance data tell you how the processis performing. Not surprisingly, you will rely primarily on performancedata at this stage of the improvement effort. To illustrate this point, lets return to the invoice payment process. Asmentioned ear

28、lier in this chapter, the team determined that it tookan average of 45 days to pay invoices. Thats performance data. Inthis case, the team would also need to document current performancefor each output characteristic, that is, the time required to moveinvoices through the mail, process them, and pay

29、 them. Performance data helps your team to identify gaps that exist betweenwhat customers expect and what you deliver, and to locate problemareas and establish a baseline. Early in the effort, your team willcollect performance data that describe current performance in “hardnumbers.” You will continu

30、e to collect performance data even afteryou have actually seen how the new process performs. This will showyou whether youve changed things for the better.Copyright 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 14Performance and Cause DataPerformance Data Descriptive Focus on Result

31、s Helps establish a baseline Measures performance of a process Should be collected firstCause Data Focuses on why process performs theway it does Helps identify potential root causes Collect this type of data to explainperformance problemsCause Data (X) Cause data, on the other hand, focuses on why

32、the process performs as itdoes. Cause data supports problem solving by helping identify Sources ofVariation (SOV) in order to isolate root causes of problems. Dont assume, however, that you shouldnt gather cause data andperformance data at the same time. Remember, resourcefulness is one of thekeys t

33、o effective data collection. Sometimes, youll know enough aboutpotential causes to measure performance and isolate potential causes at thesame time. Most of the time, however, you wont know enough about potential causesuntil youve determined your processes current performance level. Beprepared to do

34、cument current performance first, then brainstorm potentialcauses and collect additional data related to those causes at a later date.PerformanceMeasureOperationalDefinitionDataSource andLocationSampleSizeWho WillCollectthe DataWhen Willthe Data BeCollectedHow Will theData BeCollectedOther Datathat

35、ShouldBe Collectedat the SameTimeHow will the data be used?How will the data be displayed?Examples:Identification of Largest ContributorsIdentifying if Data is Normally DistributedIdentifying Sigma Level and VariationRoot Cause AnalysisCorrelation AnalysisExamples:Pareto ChartHistogramControl ChartS

36、catter DiagramsCopyright 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 15Sample Data Measurement Plan FormAdditional Department InfoCopyright 2002 Motorola. All rights reserved.Six Sigma Black Belt Program 2.2 Manage Measurement2.2 - 16Step 3.Collect DataCopyright 2002 Motorola. All

37、 rights reserved.2.2 Manage Measurement2.2 - 17Step 3: Collect Data First: Evaluate the measurement system. Then:Follow the plan note any deviations from the plan.Be consistent avoid bias.Observe data collection.Collect data on a pilot scale (optional).ReasonMissingIncorrectSocial Security NumberStr

38、eet AddressPhone NumberEmploymentInformationCopyright 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 18 The data collected will only be as good as the collection system itself.In order to assure timely and accurate data, the collection methodshould be simple to use and understand. Th

39、ere are several methods.The most common are: Checksheet - a simple log of “tick marks” representing the volume and typeof work. Time stamps - a recording of the time that each activity begins and ends.Example: ChecksheetApplications Returned for Missing Data All data can be collected manually (writi

40、ng in the log, recording the time, etc.)or automatically. Automatic data collection assures accurate and timely data,and removes the burden of collection from the operator of the process. But, itcan be very expensive to set up. It usually involves computer programmingand/or hardware. For most initia

41、l efforts, a paper log is the most cost effectiveform of data collection.Obtaining the MeasurementsWasteful Energy HabitsWeek 1Week 2Week 3TotalLong showers6Lights left on11Windows left open3oAC set below 725Door left open13Total15121138Copyright 2002 Motorola. All rights reserved.2.2 Manage Measure

42、ment2.2 - 19Identify Tools to Help You Collect DataHint: Identify types of data you need to collect before youdesign the form.ChecksheetsSimple data collectionform which helpsdetermine how oftensomething occurs.Concentration DiagramsPictorial checksheet which helpsyou mark where somethingoccurs or t

43、he type of problem.Other Loan InformationBanking Information(missing information)NameAddressTelephoneType of Loan NeededIncome LevelLoan Application.1.6223581018142215131095431Copyright 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 20Pro

44、cess Distribution ChecksheetIncoming MaterialWeight (lb.)TotalsWasteful Energy HabitsWeek 1Week 2Week 3TotalLong showers6Lights left on11Windows left open3oAC set below 725Door left open13Total15121138DefectNumberTotalIncorrect18Missing31Misfiled20Misrouted37Total106TypeDefectCopyright 2002 Motorola

45、. All rights reserved.2.2 Manage Measurement2.2 - 2112345Total241213201483TotalLot no.One-Factor Attribute ChecksheetProcess Step ReceiptDepartment SupplyTwo-Factor Attribute ChecksheetCopyright 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 22SamplingUsing a sample of data you draw

46、conclusions about the entire populationof data. This is known as “statistical inference.” Sampling saves costsand time. Sampling provides a good alternative to collecting all thedata. Identifying a specific confidence level allows us to makereasonable business decisions.Parameters:, Sampling From a

47、PopulationEntirePopulationof DataStatisticalInferenceSampleAnalysisStatistics:X, S, etc.Copyright 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 23Different situations whichdictate sampling techniques: To analyze and control aprocess.population (i.e., types ofcustomers and buyingSamp

48、ling SituationsTypical DescriptiveStatistics:Random Samplingfrom a PopulationSystematicProcess SamplingXXXSampleXXXXSampleAverage cycle time (xbar)No. of defectsProportion defectiveStandard deviation (s) To describe a largeXXXbehavior).XXXXRandomly sampling within a logical category (location, shift

49、, product, etc.)Copyright 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 24Sampling TypesProcess - subgroup samplingABBCCDDAABBCCDDDay 1XDay 3XDay 2XXXXSampleSampling from a particular step in the process each day (hour, week, month)Population - stratified random sampleSampleACopyrig

50、ht 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 25Sampling Considerations Where Location in the process where process steps directly affect outputs (strongrelationship). Maximize opportunity for problem identification (cause data). FrequencyDependent on volume of transactions and/o

51、r activity.Unstable process more frequently (use systematic or subgroup sampling).Stable process less frequently (use sample size formula).Dependent on how precise the measurement must be to make a meaningfulbusiness decision. ConsiderationsIs the sample representative of the process or population?I

52、s the process stable?Is the sample random?Is there an equal probability of selecting any data point?The answer to each of these questions must be yes before we can drawstatistically valid conclusions.Additional Department InfoCopyright 2002 Motorola. All rights reserved.Six Sigma Black Belt Program 2.2 Manage Measurement2.2 - 26Show Video Segment:SamplingDemo Bead Bowl SimulationCopyright 2002 Motorola. All rights reserved.2.2 Manage Measurement2.2 - 27Sample Size Rules of Thumb Selecting an adequate sample size, n, is a function of the risk of