Recently I learned that my companyâ??s Green Belt training no longer includes hypothesis testing; it will now be part of Black Belt training.  Is this a right decision?  I think it is, because the goal of Six Sigma training is to develop the concept of variation and use it to understand the problem, not to become a statistician.

In practice, itâ??s far more important to instill statistical thinking in an organization than to develop statisticians.

There is no argument that statistics is not an easy subject, and most people are unwilling or unable to invest the time and effort to become marginally competent in statistical methods.  Even among the well-trained scientists I know, many lack adequate statistical skills. My professional training is not in statistics. Despite years of learning and applying statistics in solving real problems in R&D, manufacturing, and process improvement, I feel confident only in the most basic problems.

My mentoring experience also shows that about 9 out of 10 Green Belts didnâ??t improve their understanding in statistics after the training. Many Six Sigma training materials and books I have seen place too much emphasis on statistical tests and methods, but little on probability theory or statistical thinking.  No wonder people getting out of the training often feel overwhelmed and confused about statistics, which is not helping the use of Six Sigma methodology.

I am sure some organizations have recognized the balance between teaching statistical thinking and training statistical methods.  As we bring Six Sigma into organizations, we have the responsibility of teaching the correct statistical concepts and tools at the appropriate levels.  More is not better.  Learned and applied incorrectly, statistics will hurt more than help our organizations and the reputation of Six Sigma.  For decades Edwards Deming urged practitioners to improve the teaching of statistics. The challenges remain to date. 

Just for fun reading, I am including a paragraph from a classic article by Deming “On Probability As a Basis For Action” published in The American Statistician (November 1975). [I highly recommend reading the entire article.]

Example 2 from my friend Dr. Edward C. Bryant. While he was at the University of Wyoming, someone came in from the Department of Animal Husbandry to announce to him an astounding scientific discovery â?? the fibres on the left side of sheep, and those on the right side, are of different diameter. Dr. Bryant asked him how many fibres he had in the sample: answer, 50,000.  This was a number big enough to establish significance. But what of it? Anyone would know in advance, without spending a dollar, that there is a difference between fibres of the left side and the right side of any sheep, or of n sheep combined. The question is whether the difference is of scientific importance.

About the Author