Step 3B: Choosing the Correct Control Chart (Continuous Data)
April 3, 2025
Just like there are many types of discrete data charts available, there are also many types of continuous control charts available. The Six Sigma process methodology prescribes which chart must be used when. The prescription in the case of continuous data points is largely based on sample size. Below is the list of the different…
If the data type that needs to be charted is discrete, then it must fall between one of binary or count types. As the name suggests in case of binary distribution, there are only two possibilities, success and failure, defective and not defective, whereas in the case of count type distribution there may be more…
As we have seen, Six Sigma is an elaborate methodology. It requires time to learn and even more time to successfully implement. However, as we have also seen that there is a golden pot at the end of the rainbow. Countless organizations have transformed their operations based on their Six Sigma capabilities. Nowadays, having processes…
Shift in the Process: A shift in the process is defined as a pattern in which seven consecutive data points appear on only one side of the mean. Statistical studies have shown that if the number of points on one side of the mean is less than 7 then it is not a non-random pattern and could have occurred due to random causes.
A shift in the process is very important for the management to detect. This is because it signifies that the average of the process has moved to a different level. Therefore, the control chart with the mean and control specifications based on old measures is redundant and will give wrong information. It is for this reason that it is important for the organization to detect this pattern as early as possible and take corresponding measures. The most common causes of the appearance of non- random shift patterns is as follows:
Process Improvement: Shifts in process means usually happen as a result of a deliberate attempt through a process improvement initiative. The best practises to do any task are continuously evolving. Introduction of new technologies enables newer and better ways of performing the work. This pattern can be detected on the control charts and the process improvement can be institutionalised.
Introduction of New Inputs: Another common reason for shift in the process mean is the introduction of new inputs. These new inputs could be markedly better or worse than the inputs used earlier and as a result change the performance of the entire process
Change in Quality Control Measures: The shift could also be the result of a change in quality control measures. The thrust may have changed from cure to prevention and as a result the quality checks may have dramatically improved the process, shifting its mean.
As the name suggests, this may be quite straightforward. However the logic behind this pattern is interesting. The normal curve states that 95% of all data points will lie between 2 standard deviations. However, if 2 out of 3 consecutive points are lying on or above the standard deviation, we can be rest assured that the 95% criteria is not being met, at least in that point in time.
This is therefore an early sign to the management that the process may be about to go out of control. A thoughtful management will make corrective action plans that will look into the process, understand the issue and correct it as soon as possible.
Your email address will not be published. Required fields are marked *