Who needs prediction markets when you can average probabilistic predictions??
Chris F. Masse April 26th, 2007
David Pennock and Daniel Reeves, cited by James Surowiecki (author of The Wisdom Of Crowds) in a comment on Midas Oracle:
[...] Clearly, for most people, averaging their own assessment with others is the right strategy. [...] As for how to aggregate probabilities, the above analysis assumes a simple arithmetic mean and we have confirmed empirically that this choice beats geometric mean, root-mean-square, and every power mean in between, regardless of the number of probabilities being aggregated. [...]
I would say “30%”, Jason Ruspini would say “50″, Steve Roman would say “40%” –> the averaged probabilistic prediction is 40%.
