Hi, 

 

When we plot review effectiveness (%) in control chart, the UCL is going beyond 100 and LCL is going below 0. However, this is not possible based on the formula of review effectiveness: Review effectiveness (%) = (Number of defects detected in reviews at a given stage) / (Sum of defect injected in that stage + number of defects slipped from earlier stages).

 

Please suggest on whether we can force fit the UCL and LCL to 100 and 0. If we do this, how can we perform trend analysis for 3 different durations. Should we look at shift in mean, stdev etc.

 

Best Regards, 

Bharani Kumar

9849312304

Dear Bharani,

 

Going by the review effectiveness definition, you would use the P chart (where the defects not found are defectives, with variable subgroup size). Please note that the chart will calculate the UCL and LCL based on the data that you use unless you specify the limits, which can be done by clicking on P-chart options -> Limits. 

 

If you choose to test for all Special Causes (P chart options - > tests), it will show if the variable is out of control even for reasons other than >1 std dev from mean.