Most Societies for Quality milk millions of dollars from trusting members, by teaching statistics that are irrelevant to Quality. Such statistics do not improve members' processes. 90% of members' processes are a disaster zone. (Dr Wheeler )
Bamboozling companies with traditional statistics is ignorant. Hawkers of the Six Sigma Scam use totally irrelevant statistics to pad courses, to justify outrageous prices. The self-confessed con man who created the Scam, charged $70,000 per victim.
TRADITIONAL STATISTICS WARNING
Professor Deming warned about such practices. He said: "Analysis of variance, t- test, confidence intervals, and other statistical techniques taught
in the books, however interesting, are inappropriate because they bury the information contained in the order of production." "The student should
avoid passages in books that treat confidence intervals and tests of significance, as such calculations have no application in analytic problems in
science and industry."
Dr Gulen says that at GE, "It was sad and funny simultaneously" that the statistics in Six Sigma courses went way over the heads of 80% of the class. Teaching employees irrelevant statistics, is ludicrous.
TRADITIONAL STATISTICS USE
Traditional statistics can tell you that last years' production is probably worse than the year before ... IF a set of assumptions is satisfied ...
and usually they are NOT. Traditional statistics cannot tell you what is important to quality and what you really need to know. That is, traditional
statistics cannot tell you if you are producing good quality and that you will still be producing good quality next week.
CONTROL CHARTS
There is only one way to tell if you are producing good quality and that you will be producing good quality into the future. That is, the Process
Behavior Chart, (Shewhart, or Control Chart). Control Charts do NOT depend on the assumptions of traditional statistics.
Control Charts are fundamentally different to traditional statistics. They incorporate time. The sequence of data from production is key. Traditional statistics ignore time. Traditional statistics make no distinction whether samples were taken from anywhere in a warehouse or from the end of a production line.
Most importantly, Control Charts are simple to use by ANY employee, WHEN USED CORRECTLY. Despite their ease of use, Sick Sigma hacks make a mess of them. As one intelligent but exasperated young man said to me: "I had to pretend that 'control charts require normality' was a 'correct' answer during the CQE certification exam."
SUMMARY
Teaching traditional statistics by Quality Associations and other hacks, has made a lot of money for these hawkers of the Six Sigma Scam.
Professor Deming said: "American management have resorted to crash courses in statistical methods, employing hacks for teachers. The result is
that hundreds of people are learning what is wrong."
by Dr Tony Burns BE (Hon 1) PhD (Chem Eng)