Subject: (Maxey) Probability of an association.....
Date: Wed, 12 May 1999 104724 -0500 (CDT)
From: "Roy L. Beavers" <rbeavers@llion.org>
To: emfguru <rbeavers@llion.org>
--------------------------------------------------
.......Cleaning out some files today..... Here is one that I have been
intending to send when things "slowed down" a bit..... Ed Maxey and
Chris Reuss (both of this list) have been trying yo get someone to argue
with them about these calculations, without success......
Roy Beavers (EMFguru)
rbeavers@llion.org................
...It is better to light a single candle than to curse the darkness...
.................PEOPLE ARE MORE IMPORTANT THAN PROFITS...............
.......DO YOU KNOW OF OTHERS WHO SHOULD BE ON THIS LIST?????..........
---------- Forwarded message ----------
Date: Wed, 28 Apr 1999 17:22:14 -0500
From: Edward S Maxey
To: creuss@bluewin.ch
Cc: rcmahq@nwark.com, rbeavers@llion.org
Subject: Ozarks
Hello Christoph Reuss,
You will remember having provided the Sigma notation for determining
probabilities in June of 1988. You were given full credit for the
formulation
at the annual meeting of Ozarks Electric Cooperative Corp. today. This
cooperative services some 43,000 here in Arkansas.
John Clark, a retired Professor of Mathematics and Computer
Science at Orange Coast College in California, understood your
formulation immediately and very kindly wrote a computer program
in Pascal which implements it.
Here is the output shown to the folks of Ozarks Electric today:
* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
* * * *
Sigma Notation
P [H<=QC] = 1/2^TC * SUM(k=0..QC) (TC! / (TC-k)! / k! )
- where -
TC = Total Cases; values up to 4096.
QC = Questioned Cases; values from 1 to TC.
Please enter your Total Case number now 624
Please enter your Questioned Case number now 215
The results are
NUMERATOR = 2.35216114028153E+0173
DENOMINATOR = 6.96173189944793E+0187
QUOTIENT = 3.37870112531633E-0015
RECIPROCAL = 2.95971724905491E+0014
The odds of chance alone yielding 215 or less
Questioned Cases out of 624 Total Cases are one
in 295,971,724,905,491.
* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
You may wonder about the 215 input number. The Electric
Power Research Institute in a 1993 study of approximately
1, 000 homes throughout the United States determined that
the median time weighted average for residences was 0.5 mG.
The Linet study did not provide a median for the 624 cases included
in Table 2 (below in modified form) but did provide segments of
0 - <0.65, 0.65 - 0.99 and 1 - 1.99. If one assumes the cases were about
evenly spread in the 0.65 - 0.99 segment there would be 52 cases in
a segment of 0.15 mG. If one subtracts 52 from 267 we have 215, an
approximation probably on the full side, which can be used as the
number of Linet's cases which came from abodes below the
United States 0.5 mG median.
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
Table 2. Risk of Childhood Acute Lymphoblastic Leukemia !
According To Time-Weighted Average Summary Levels of !
60-Hz Residential Magnetic Fields In The Unmatched And !
Matched Analysis
!
!
Magnetic-Field
!
Level (mG) No. Of Cases Cases./0.01mG increment !
<0.65 267 4.11
!
0.65-0.99 123 3.51
!
1.00-1.99 151 1.51
!
=>2.00 83
!
Note: Values converted to milligauss from
!
microtesla in the original.
!
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ !
If it is convenient, please run your computer program with input
values of 624 and 215 to confirm the 295,971,724,905,491result
obtained here.
Please also note that 62.5% of Linet's cases came from abodes
of under 1 mG ambient field. This should be taken very seriously!
We should avoid suggesting that exposure of up to 1 mG is in any
way safe. It seems likely, when all is said and done, that we will find
Dr. Robert Becker's "theoretical safe limit" of 0.3 mG is about right.
Again, many thanks for emailing the SIGMA notation.
Cordially,
Ed Maxey
___________________________________________________________________
You don't need to buy Internet access to use free Internet e-mail.
Get completely free e-mail from Juno at http://www.juno.com/getjuno.html
or call Juno at (800) 654-JUNO [654-5866]
Archive provided courtesy of WaveGuide, http://www.wave-guide.org
Reprinted with permission of Roy Beavers, http://www.feb.se/EMF-L/EMF-L.html