Around 1985 Bill Smith, the originator of Six Sigma, working at Motorola, had noticed “sudden shifts” in process averages. Bill found typical shifts of the order of 1.5 sigma. Under normal situations this would immediately have been recognised as being the result of a special cause. That is, sudden shifts in a process are the result of a change, an abnormal event. Whether attempts were made to remove these special causes is lost in history. Perhaps the cause could not be removed, such as raw material from two different suppliers. Whatever the cause, it was decided to make an allowance for these “sudden shifts” by broadening the specification limits. (Ref” “Ask Dr Harry”)

In 1985 Mikel Harry linked up with Bill Smith at Motorola. Between 1985 and 1988 Harry developed a “theory” to try to explain the shifts in process averages. Harry refers to a paper written in 1975 by Evans, “Statistical Tolerancing: The State of the Art. Part 3. Shifts and Drifts”. The paper is about tolerancing. That is how the overall error in an assembly is effected by the errors in components. Evans refers to a paper by Bender in 1962, “Benderizing Tolerances – A Simple Practical Probability Method for Handling Tolerances for Limit Stack Ups”. He looked at the classical situation with a stack of disks and how the overall error in the size of the stack, relates to errors in the individual disks. Based on “probability, approximations and experience”, he suggests:

V = SQRT( var X )

What has this got to do with monitoring the myriad of processes that people are concerned about? Very little, if anything. Harry then takes things a step further. Imagine a process where 5 samples are taken every hour (MSA TS16949 Automotive Quality Management Standard) and plotted on a control chart. Harry considered the “instantaneous” initial 5 samples as being “short term” (Harry’s n=5) and the samples during the following 10 hours, as being “long term” (Harry’s g=50 points). Because of random variation in the first 5 points, the mean of the initial sample is different to the overall mean. Harry derived a relationship between the short term and long term capability, using the equation above, to produce a capability shift or “Z shift” of +/-1.5 ! Over time, the original meaning of instantaneous “short term” and the 50 sample point “long term” has been changed to result in “long term” drifting means.

Harry has clung tenaciously to the “1.5” but over the years, its derivation has been modified. In a recent note from Harry “We employed the value of 1.5 since no other empirical information was available at the time of reporting.” In other words, 1.5 has now become an empirical rather than theoretical value. A further softening from Harry: “… the 1.5 constant would not be needed as an approximation”.

Hence we see that the 1.5 sigma shift started as being “sudden”, then a “long term” of half a day, then folklore turned “long term” into an undefined “long term”. The shift started as an observation of a special cause, then changed to an erroneous theory, then changed to an approximation that is “not needed”. Nevertheless, the 1.5 shift became a foundation stone of Six Sigma.

One might have thought the idea that all process means drift by such a huge amount in an uncontrollable way would go against common sense. Despite this, no one has bothered to check it ! The consequences are profound. It has led to claims of “3.4 DPMO”. Consultants such as Praveen Gupta and no doubt many others, claim that all processes unavoidably are out of control “13%-14%” of the time because of this shift. If this were true, American industry would be on it’s knees. The greatest consequence is that American industry now sees that drifts in process averages are “normal” and nothing to be concerned about. People have forgotten that world class quality means ON TARGET with minimum variation.

Does anyone have any additions to this account?