【正文】 values less than indicate poor agreement. Repeat above step, we can got following kappa measures for the appraisers: Table 4 Analysis Techniques: Attribute Gage Study Σ aΣ ef NΣ ef Ka p p a A B C A B C Table 4 Using the same steps to calculated the kappa measure to determine the agreement of each appraiser to the reference decision: Table 5 Total summary on Table 6: Analysis Techniques: Attribute Gage Study A B C K app a Table 5 S ourc e A p p ra i s e r A A p p ra i s e r B A p p ra i s e r CT ot a l Ins p e c t e d 50 50 50 M a t c he d 44 46 43M i x e d 6 4 795%U CI % % %Ca l c ul a t e d S c ore 88% 92% 86%95%L CI % 81% % T ot a l Ins p e c t e d 50 i n A g re e m e nt 4295%U CI % Ca l c ul a t e d S c ore 84%95%L CI %%S c ore vs A t t ri but eA n n e B e n C a t h y7 58 59 5A p p r a i s e rPercentW i t h i n A p p r a i s e rA n n e B e n C a t h y7 58 59 5A p p r a i s e rPercentA p p r a i s e r v s S t a n d a r dA s s e s s m e n t A g r e e m e n tD a t e o f s t u d y :R e p o r t e d b y :N a m e o f p r o d u c t :M i s c :[ , ] 9 5 . 0 % C IP e r c e n tAnalysis Techniques: Attribute Gage Study Analysis Techniques: Attribute Gage Study The AIAG MSA reference manual edition 3 provides acceptability criteria for each appraisers results: Definition: False Alarm – The number of times of which the operator (s) identify a good sample as a bad one. Miss – The number of times of which the operators identify a bad sample as a good one. D eci si on M easu r em ent S y st e m E f f ect i venes s Mi ss R at e Fal se A l arm R at e A cce pt abl e f or appr ai ser ≥ 90% ≤ 2% ≤ 5% M ar gi nal l y accept abl e f or t he app r ai ser m a y need i m pr o v e m ent ≥ 80% ≤ 5% ≤ 10% U nac cept abl e f or t he appr ai ser needs i m pr o v e m ent s 80% 5% 10% Number of correct decisions Total opportunities for a decision Effectiveness = Analysis Techniques: Attribute Gage Study Number of False Alarm Total opportunities for a decision False Alarm Rate = Number of False Alarm Total opportunities for a decision Miss Rate = So summarizing all the information of the example with this table: Table 7 F als e A l ar m R at eA 88% 4% 8%B 92% 6% 2%C 86% 8% 14%E f f e c t i ve n e s s M i s s R at eAnalysis Techniques: Attribute Gage Study Conclusion: The measurement system was acceptable with appraiser B, marginal with appraiser A, and unacceptable for C. So we shall determine if there is a misunderstanding with appraiser C that requires further training and then need to redo MSA. The final decision criteria should be based on the impact to the remaining process and final customer. Generally, the measurement system is acceptable if all 3 factors are acceptable or marginal. Minitab also can perform attribute gage analysis, but it didn’t declare the acceptability criteria, so it is not recognized by QS9000 standard. Analysis Techniques: Attribute Gage Study ? Signal Detection Theory is to determine an approximation of the width of the region II area so as to calculate the measurement system GRamp。R base on the tolerance (P/T ratio). If the measurement system is going to be use for process optimization /characterization analysis, then we should use the %Ramp。R (P/P ratio: % total of total variance。R statistics are then calculated as follows: 2222 ropo SSSS m s ???Measurement Error: Part: tnSnSPMSPV rop 22)( ??? Operator: pnSnSOMSOV rop 22)( ???Interaction: nSOPMSIV r2)( ?? Reproducibility: 22 IVOVAV ??Repeatability: M S EEV ? Measurement Error: 22amp。 the interaction effect is estimated by ?op2。R is that it does not consider the variation introduced into a measurement through the interaction between different conditions (appraiser) and the gage. Consequently, to account for this variation an analysis of variance method (ANOVA) is utilized. In addition, when the sample size increases, use of the range to estimate the variation in not very precise. Furthermore, with software packages readily available, the ANOVA method is a viable choice. The total variation in an individual measurement equals: The part to part variation is estimated by ?p2。R and the part variation 3KRPV p?22amp。amp。 AVEVRR ??1 00*amp。R (P/P ratio, %Ramp。R) The gage error (Ramp。R Study: The Average and Range Method The ANOVA Method The mon step for conducting Gage Ramp。R). The %Ramp。R means Gage repeatability and reproducibility, which bined estimate of measurement system repeatability and reproducibility. This bined measurement error then is pared with the process output variability to pute the gage percentage Ramp。 Gage Ramp。R Reproducibility is the variation in the average of the measurements made by different appraisers using the same gage when measuring the identical characteristics of the same part. It is betweensystem variation, monly referred to as Variation. Reproducibility Introduction: Where does the variation of measurement system e from? ? The Five Characterizations of Measurement System: 2. Width Variation: Repeatability。 Reproducibility。 Gage Ramp。 Linearity Linearity is the difference in the bias values through the expected operating range of the measurement instrument. It is a systematic error ponent of the measurement system. Linearity Introduction: Where does the variation of measurement system e from? ? The Fi