Re: Rule of Thumb?

[DANSWART@aol.com]

In a message dated 8/7/99 9:40:32 PM Pacific Daylight Time, 
Kromkowski@aol.com writes:

<< 4. My very specific question in my original post:  "By what method does 
one 
 tell the difference between professional management judgment and management 
 lack of understanding of variation?"
 
 --
 John David Kromkowski >>

---------------------
JD,

Are they two separate things requiring differentiation (either/or)?  Since 
data can never be conclusive, judgment will ALWAYS be present (professional, 
management, or otherwise).  Management lack of understanding of variation 
may, or may not be present.  Since one condition is always present, and the 
other may or may not be, the distinction in the question seems misstated.

You can only evaluate management's understanding of variation as it relates 
to a specific judgment.  Do this by evaluating the presentation of the data 
used to support the judgment, along with the explanation, and the choice of 
action which follows the judgment.  If the explanation of the data includes 
analysis that, in your opinion or those of experts you agree with, has the 
best chance of separating the signal from the noise, the data analysis has 
gone as far as possible given the time constraints of the decision that must 
be made.  The analysis may provide a high degree of confidence that a signal 
is present, or may be entirely inconclusive, or somewhere in between.  The 
action chosen should be consistent with the analysis results.  If the 
analysis is inconclusive and still a decision must be made, it may be 
tampering.  Without a control chart the assumption is that it is likely 
tampering.  Still, some decisions cannot be delayed.  Based on your own 
judgment of the methodology and consistency of the action with the aim, you 
can then support the judgment or disagree with it.  Confidence in a judgment 
should be based on the laws of probability and/or the analysis of variation 
developed by Shewhart and Deming, depending on the nature of the inquiry 
(enumerative or analytical).

The method of determining management's understanding of variation is to ask 
"Where is your data? and How do you know?"  

I would point out that the choice of three-sigma on the control chart is a 
rule of thumb by Dr. Shewhart and has proven very useful, and there has been 
much discussion on this list as to the relative merits of this rule.

Would a better question be, "By what method does one tell when professional 
management judgment shows a lack of understanding of variation?"

Dan
danswart@aol.com
=========================================================================