【正文】 s Pass Pass Pass Pass 9 Fail Fail Fail Fail Fail Fail Fail 10 Pass Pass Pass Pass Pass Pass Pass 11 Pass Pass Pass Pass Pass Pass Pass 12 Pass Pass Pass Pass Pass Pass Pass 13 Pass Pass Pass Pass Pass Pass Pass 14 Pass Pass Pass Pass Pass Fail Pass 15 Fail Fail Fail Fail Fail Pass Fail 16 Pass Pass Pass Pass Pass Pass Pass 17 Pass Pass Pass Pass Pass Pass Pass 18 Pass Pass Pass Pass Pass Pass Pass 19 Fail Fail Fail Fail Fail Fail Fail 20 Pass Pass Pass Pass Pass Pass Pass 21 Pass Pass Pass Pass Pass Pass Pass 22 Pass Fail Fail Pass Pass Pass Pass 23 Pass Pass Pass Pass Pass Pass Pass 24 Pass Pass Pass Pass Pass Fail Pass 25 Fail Fail Fail Fail Fail Fail Fail 26 Pass Pass Pass Pass Pass Pass Pass 27 Pass Pass Pass Pass Pass Pass Pass 28 Pass Pass Pass Pass Pass Pass Pass 29 Fail Fail Fail Fail Fail Fail Fail 30 Pass Pass Pass Pass Pass Pass Pass Operator 1 Operator 2 Operator 3 Attribute MSA Example Open file: Copyright 169。, Breakthrough Change StrategySM, Breakthrough DesignSM, Breakthrough DiagnosisSM, Breakthrough ExecutionSM, Breakthrough Sigma LeanSM, Breakthrough Six SigmaSM, Breakthrough Software DesignSM, FASTARTSM, Six Sigma Gold BeltTM, SOLVING YOUR BUSINESS PROBLEMS FOR THE LAST TIMESM. Six Sigma is a federally registered trademark of Motorola, Inc. MINITAB is a federally registered trademark of Minitab, Inc. SigmaFlow is a federally registered trademark of Compass Partners, Inc. VarTran is a federally registered trademark of Taylor Enterprises. Copyright 169。 20232023 32 Measurement Systems Analysis (MSA) Attribute Statistical Report Continued Copyright 169。 for use only in pliance with SSA license. Attribute MSA Method Step 1: Select a minimum of 30 parts from the process 至少選擇 30個部件 50% of the parts in your study should have defects/ 50%有缺陷 50% of the parts should be defectfree/ 50%沒有缺陷 If possible select border line (or marginal) good and bad samples / 盡可能選擇界限附近的好的和不好的樣品 Step 2: Identify the appraisers which should be qualified / 選擇有資格的評價者 Step 3: Have each appraiser, independently and in random order, assess these parts and determine whether or not they pass or fail / 每個評價者隨機評價部件，確認是否通過或不通過 Step 4: Enter the data into Excel or MINITAB to report the effectiveness of the attribute measurement system / 輸入 Excel或 MTB 報告屬性數(shù)據(jù) MSA的有效性 Step 5: Document the results. Implement appropriate actions to fix the inspection process if necessary / 結(jié)果文件化，如有必要，進行相應(yīng)的改善 Step 6: Rerun the study to verify the fix / 再運行 MSA，驗證改善有效 Note: A 30piece sample will yield an estimate of appraiser efficiency and capability which has a fair amount of uncertainty. Typically a larger sample is not needed because the appraisal process is obviously ineffective. The Excel spreadsheet can handle up to 100 samples Copyright 169。 assessments agree with each other. Fleiss39。你的任務(wù)就是識別不合格的文件。 2個評價者獨立評價隨機在不同日期抽取的 10張發(fā)票。 30/70 ratio is acceptable – Beyond this level, single disagreements can have large leverage on the Kappa / 計算 Kappa，為了最大化信賴性，最好 good/bad的部件各占 50%， 30/70也是可以接受的 – 超過這個限度，單個的不一致對 Kappa有很大影響 ? Execution 實施 Parts should be rated in random order independently (no parisons) 部件應(yīng)該以隨機順序評價 Study should be blind 研究應(yīng)該是盲測 Categories need to be mutually exclusive and exhaustive 分類既不重復也不遺漏 Rating time should be similar to that “normally” used 評價時間也和正常使用相同 14 Measurement Systems Analysis (MSA) Attribute Guidelines For Kappa Studies (Cont’d) ? Analysis 分析 Review the repeatability portion first (Within Appraiser Kappa), if an Appraiser cannot agree with themselves, ignore parisons to other Appraisers and go understand why (see Improvement below) 先檢查重復性的部分 (評價者內(nèi)的 Kappa)，如果評價者自己不一致，忽略和其他評價者的比較，而要找出原因 (看下面的改進 ) For Appraisers that have acceptable repeatability, review the reproducibility portion (Between Appraiser) 如果重復性可接收，檢查再現(xiàn)性部分 (評價者之間 ) If a “Gold Standard” is available (ratings of the samples known by some other means as being “correct”), pare each Appraiser to them for “calibration” / 如果 ”標準 ”已知 (已知的正確的等級 )，通過比較每個評價者和已知值來校正 ? Use the field in MINITAB, “Known Standard Attribute” 用 MTB中 “Known Standard Attribute”一欄 ? Improvement 改進 If the Within Appraiser Kappa scores are low, that Appraiser may need training. Do they understand characteristic they are looking for? Are the instructions clear to them?/ 評價者內(nèi) Kappa 值較低，那么就需要培訓，他們是否理解檢查的特性？是否清楚作業(yè)指導書？ If the Between Appraiser Kappa scores are low, each Appraiser may have a differing definition of the categories – A standardized definition can improve this situation / 評價者間 Kappa 值較低，那么每個評價者對零件分類的定義不同 –標準定義可以改變這種狀況 If improvements are made, the study should be repeated to confirm improvements have worked /如果已進行了改進，還需要再次研究以確認改進有效 15 Measurement Systems Analysis (MSA) Attribute ? Recall what ordinal data is – Categorical variables that have three or more possible levels with a natural ordering, such as strongly disagr