RE: Special Causes Indicators in Red Bead

[Steven_S_Prevette@rl.gov]

I cannot speak for Dr. Deming, but I have (out of approximately 60
experiments) picked up 2 or 3 indicators of special cause variation.  False
alarms are going to happen, they cannot be eliminated entirely.  The
explanation would be that based upon knowledge of the physical system in
place, the signal is most likely a false alarm.

Except .  . .

Acheson Duncan's Quality Control and Industrial Statistics states (in an
argument supporting Cusum control charts) "Experiments with sampling from
the [red bead] box suggested that something in the character of the red
beads caused them to drift to the top of the box, and when samples were
taken by sliding the paddle in along the bottom, they showed a downward bias
in the number of red beads obtained".  Pages 514 and 515.

Dr. Deming definitely tied a discussion of "mechanical sampling" in with
explaining the results of the Red Beads, especially using the example of the
quantity of ore in samples of ore being shipped to Japan from the U.S.  I do
also know that Phil Monroe and Bill Cooper once had an attack of static
electricity, and were retrieving practically only red beads from the box on
a visit here to Hanford (in a dry, desert environment).

Steve Prevette
Site Technical Authority for Statistical Trending
Environment, Safety and Health
Fluor Hanford, A Fluor Global Services Company
ASQ Certified Quality Engineer
steven_s_prevette@rl.gov
509-373-9371