Hello, again, Paul > In effect, when forecasting snow, one should ignore priors and listen to The > Weather Channel.
Pooling forecasts (like yours and the Weather Channel's) can be done in a variety of ways, even within arguable Bayesian orthodoxy. If you believe the Weather Channel is well calibrated, and have no such confidence in your own forecast, then adopting their forecast sounds like a plan. In any case, the Bayes' ratio that reconciles _your_ prior probability to _their_ posterior probability wouldn't seem to be helpful to you. Paul _______________________________________________ uai mailing list [email protected] https://secure.engr.oregonstate.edu/mailman/listinfo/uai
