JFK Witness Deaths: A Guide to the Probability Calculations
May 27, 2013
Updated: Oct.15, 2013
JFK Blog Post Index: Richard Charnin JFK Blog Posts
An actuary engaged by London Sunday Times calculated 100,000 TRILLION to 1 odds against 18 JFK material witness deaths from Nov. 1963 to Feb. 1967. Unfortunately, the actuary could not be identified and interviewed since no one at the Sunday Times could recall his or her name.
The House Select Committee on Assassinations (HSCA) claimed that the number of material witnesses was unknowable and dismissed the calculation as invalid. But exactly 552 Warren Commission witnesses testified, a subset of approximately 1400 material witnesses.
Here are the graphs and probability calculations which prove a conspiracy: http://richardcharnin.wordpress.com/2013/10/14/jfk-witness-deaths-graphical-proof-of-a-conspiracy/
In fact, the actuary’s odds are conservative. There were at least 42 unnatural witness deaths in the three years following the assassination. Assuming 1400 material witnesses, the probability is ZERO.
The JFK Witness Spreadsheet Database includes 118 material witnesses, of which there were at least 83 unnatural deaths. The sensitivity analysis tables display unnatural death probabilities for 552 Warren Commission and 1400 material witnesses (based on unnatural, weighted and homicide mortality rates) over 1,3 and 14 year time intervals.
According to the reference Who’s Who In the JFK Assassination approximately 1400 material witnesses were connected in any way to the assassination. At least 83 died unnaturally. The probability is ZERO.
Convenient deaths spiked in 1964 (Warren Commission) and 1977 (House Select Committee).
Warren Commission apologists have suggested that there were many more than 1400 material witnesses and therefore the probabilities are not valid – without providing a list. Even assuming there were 25,000 witnesses, then given the 0.00006 average homicide rate, the probability of 24 homicides within three years following the assassination is 1 in 12 billion. So much for the bogus 25,000 witnesses argument.
The unweighted unnatural rate results in virtually ZERO probabilities. But since the JFK-related deaths were mostly homicides, the weighted average rate is a theoretically superior rate to use for the probability calculations – and results in significantly lower probabilities than the unweighted (national) rate. But even the weighted rate is too high, since many witness “suicides” and “accidental” deaths were clearly homicides. If all of the unnatural deaths were in fact homicides, the probabilities are at their lowest.
The unweighted unnatural mortality rate produces virtually zero probabilities for both the Warren Commission (552) and material witness (1400) groups, so it may appear to be overkill to use the lower weighted average and homicide rates to calculate the probabilities. But they illustrate 1) the implausible ratio of homicides in the total witness mix, and 2) the inflating effects of “suicides” and “accidental” deaths in the probability calculations.
At least 62 of the 118 witnesses in the database testified or died suspiciously shortly before they were due to testify at the 1964 Warren Commission, 1969 Garrison/Shaw trial, the 1975 Senate Intelligence hearings and the 1977 HSCA (including 7 top FBI officials in June-November 1977). There were at least 37 unnatural and suspicious deaths of approximately 1100 witnesses who were called to testify. The probability is 4.7E-30 (1 in 200,000 MILLION TRILLION TRILLION).
The HSCA made the following errors:
1) misstated the actuary’s method of calculation
2) Did not consider that there were over 80 unnatural at least 30 other suspicious deaths
3) did not consider suspicious deaths of HSCA witnesses (7 FBI) just prior to their scheduled testimony
4) did not run a sensitivity analysis of probabilities for various data assumptions
5) ignored unnatural mortality rates in calculating the probability of unnatural deaths
6) did not use the POISSON distribution function to calculate probabilities
7) did not calculate probability of 11 WC homicides in 15 years.
8) ignored the fact that the JFK homicide rate far exceeded the national rate
9) did not calculate the ZERO probability of 83 unnatural deaths for 1,400 witnesses (1964-78)
10) did not calculate probability of 25 homicides in three years for an impossible 25,000 witnesses
The key to calculating the probability of a given number (n) of unnatural deaths occurring in a given group (N) in a given time period (T) is to recognize that it is based on the difference between expected and actual unnatural deaths. The larger the discrepancy between the actual observed and expected number of deaths, the lower the probability.
These are the relevant probability input parameters:
n= number of observed unnatural deaths
N= total number of witnesses
T= time period in years
R= unnatural mortality rate
The expected number of unnatural deaths E = N*T*R