Control limits are the limits of expected variation of either ‘individuals’ data or sample (subgroup) data. Typically, the acceptable limits of variation equates to what one would expect to see in a random process 99.73% of the time.
Use: One way that a Six Sigma practitioner can determine whether or not they have a ‘smoking gun’ – meaning that they have unexpected variation, is if a point goes out of control on a control chart. This is to be viewed as an opportunity for improvement. The probability of that point going beyond the limit of expected variation randomly is less than 0.0027%.
In fact, consider that the farther that a point is beyond a control limit means that the probability of that happening just by random chance is greatly diminished and gives you much greater than 99.73% confidence that something is significantly changed in the process.
