measurementsystemanalysis解析.ppt

* P观察到的＝0.7 P偶然的＝（P1好×P2好）＋（P1坏×P2坏）=0.8×0.5+0.2*0.5＝0.5 Kappa=(P观察到的－P偶然的)/（1－P偶然的）＝(0.7-0.5)/(1-0.5)=0.4 * P观察到的＝0.7 P偶然的＝（P1好×P2好）＋（P1坏×P2坏）=0.8×0.5+0.2*0.5＝0.5 Kappa=(P观察到的－P偶然的)/（1－P偶然的）＝(0.7-0.5)/(1-0.5)=0.4 * P观察到的＝0.7 P偶然的＝（P1好×P2好）＋（P1坏×P2坏）=0.8×0.5+0.2*0.5＝0.5 Kappa=(P观察到的－P偶然的)/（1－P偶然的）＝(0.7-0.5)/(1-0.5)=0.4 * P观察到的＝0.7 P偶然的＝（P1好×P2好）＋（P1坏×P2坏）=0.8×0.5+0.2*0.5＝0.5 Kappa=(P观察到的－P偶然的)/（1－P偶然的）＝(0.7-0.5)/(1-0.5)=0.5 * Attribute Gage RR Study Attribute Gage RR Study for Measurement Within Appraiser 重复性偏差(评估财务稽核人员自身的误差） Assessment Agreement Appraiser # Inspected # Matched Percent (%) 95.0% CI 1 15 15 100.0 ( 92.8, 100.0) 2 15 13 86.7 ( 59.5, 98.3) 3 15 14 93.3 ( 68.1, 99.8) # Matched: Appraiser agrees with him/herself across trials. 结果显示1 * Each Appraiser vs Standard Assessment Agreement 每个财务稽核人员的检验结果与真值的比较 Appraiser # Inspected # Matched Percent (%) 95.0% CI 1 15 14 93.3 ( 68.1, 99.8) 2 15 13 86.7 ( 59.5, 98.3) 3 15 14 93.3 ( 68.1, 99.8) # Matched: Appraisers assessment across trials agrees with standard. 结果显示2 * Assessment Disagreement # 合格/ # 不合格/ Appraiser 不合格 Percent (%) 合格 Percent (%) # Mixed Percent (%) 1 1 16.7 0 0.0 0 0.0 2 0 0.0 0 0.0 2 13.3 3 0 0.0 0 0.0 1 6.7 # 合格/不合格: Assessments across trials = 合格 / standard = 不合格. # 不合格/合格: Assessments across trials =不合格 / standard = 合格. # Mixed: Assessments across trials are not identical. 结果显示3 判错率：5％可接受 * Between Appraisers Assessment Agreement 再现性偏差(评估财务稽核人员之间的误差) # Inspected # Matched Percent (%) 95.0% CI 15 13 86.7 ( 59.5, 98.3) # Matched: All appraisers assessments agree with each other. 结果显示4 * 结果