Using Process Report to Identify Increase in Process Variabilitymain topic
Using Process Report to Identify Increase in Process VariabilitySuppose you have a process with a target of 40, a lower specification limit of 38, and an upper specification limit of 42. You collect data in subgroups of size 5 and have found that your process is nearly centered on target (process mean = 40.0016 and ST standard deviation = 0.960).
You add another 20 subgroups of size 5, and the ST standard deviation increases to 2.
The process reports show:
The Cumulative DPMO lines become fairly flat but then exhibit upward slopes. In this case, the ST DPMO line has a more pronounced upward slope than the LT DPMO line. The process has changed and an investigation can help determine the assignable cause.
The Cumulative Statistics report reveals:
1 An increase in both LT and ST standard deviations
2 A change in slope for both ST and LT
3 No change in the mean
The ST standard deviation doubled from 1 to 2. That change was so dramatic that it actually dominates the decomposition of total process variability. In other words, the SS Between component of variation becomes so small relative to the SS Within component, that the SS LT and SS ST lines become almost parallel.
These results lead to one conclusion: the inherent variability of the process has increased. A change in process variability affects SS Within subgroups, which is a component of both ST SS and LT SS. You can readily see in the Cumulative SS plots the change in slopes that occur at subgroup 50. You can also see an obvious change in the Cumulative StDev plots, but it is less clear where the change occurs. The Cumulative SS plot better displays the nature of the change, as well as the point where the change occurs.
This report displays the effect that the increase in process variability has on the Z statistics.
When you see behavior such as this, do not use the Process Report as is. The report is based on two different processes and you need to determine which process you want to perform the analysis on - the one before or after the change. Once you have made that determination, collect data only from that process and rerun Process Report. If Process Report is used to validate project improvements, do not include data collected before the improvements.