From: Harvey Newstrom (mail@HarveyNewstrom.com)
Date: Mon Jun 02 2003 - 17:44:30 MDT
The Doomsday Argument is silly. I don't understand how it can be considered
a valid use of statistics in the first place. To get an accurate estimate,
we must pull a random sample from the entire population pool. In the case
of the Doomsday Argument, which purports to do statistical analysis on all
populations past and future, we would need to pull random samples from all
time periods including past and future. Any sampling which does not pull
examples from the future is incomplete and will skew the measurement toward
our current time.
Future civilizations are not represented in our random sampling. By
sampling at this current point in time, we are excluding future
civilizations. Therefore, there is nothing unusual about the fact that our
numbers are skewed toward the present time, or that future populations are
not represented in our statistics. It is circular logic to pull a random
sample that excludes the future and then turn around and note that the
future is not represented in the data.
We can demonstrate the validity of my argument by looking in the past. It
is argued that the Doomsday Argument is valid for all period in the past,
even though it turned out to be wrong. I submit that it was never valid.
Looking backwards, we can randomly sample people from the ancient caveman's
past and future. In doing so, we do not find an over-represented number of
people in the past. The numbers keep expanding into the caveman's future.
Looking backwards, we can see the true results and the fact that the
Doomsday Argument failed to accurately measure it. Thus, as a tool, it has
continuously failed. It has never been successful as a predictive tool.
Furthermore, we can build a simulation of our future civilization and
measure it. Even in a civilization that expands forever, we find that the
Doomsday Argument incorrectly samples its own time period and fails to
predict the future. We can see in the simulation that it would always fail
to produce the correct data. It does not matter if we simulate doomsday
scenarios or immortal scenarios, the Doomsday Argument does not and cannot
change. It is a broken meter that is not measuring anything about the
future.
-- Harvey Newstrom, CISSP, IAM, GSEC, IBMCP <www.HarveyNewstrom.com> <www.Newstaff.com>
This archive was generated by hypermail 2.1.5 : Mon Jun 02 2003 - 18:00:26 MDT