Understanding Variation

When the topic of variation is discussed, the context is normally control charts and statistical process control. One of the specialists in understanding variation that has influenced members of the SEI as well as many other diverse fields such as transportation, manufacturing, utilities, and aerospace is Dr. Donald Wheeler. Dr. Wheeler is an internationally recognized speaker and trainer in the understanding and use of data in business and industry. Dr. Wheeler holds a Ph.D. in statistics from Southern Methodist University and was a student and associate of Dr. W. Edwards Deming for 19 years. Dr. Wheeler has written numerous technical books on statistical process control and related topics, but the one book that continues to have a visible impact on those who strive to fully understand and use CMMI at higher maturity levels is [1].

In Chapter 2 of [1], Dr. Wheeler discusses Dr. Walter Shewhart's approach to interpreting data:

We analyze numbers in order to know when a change has occurred in our process of system . Some variation is routine, run-of-the-mill, and is to be expected even when the process has not changed. Other variation is exceptional, outside the bounds of routine, and therefore to be interpreted as a signal of process change . The key to effectiveness of the process behavior chart is contained in the way in which the limits are computed from the data . If over a reasonably long period of time, all of the points fall within the...