I just submitted the following letter to the Salon editor, responding to:
http://www.salon.com/tech/feature/2000/11/16/election_prediction/index.html
Not Every Error is a Failure
If the newspaper forecasts sun, but it rains on your parade, does that mean
you should never again read their forecast? Of course not. If you can
find a more reliable source of forecasts, you should switch. But if not,
you should make do with the best source you can find, even if it is
sometimes in error.
Recently the Iowa Electronic Markets (IEM) only assigned a 30% chance to
Gore winning the popular vote. Dalton Conley thus suggests that economists
to go back to the drawing board, and retract their claim that such markets
consistently predict elections better than opinion polls and other
forecasting institutions. But this is no better than rejecting the
weatherman because it rained once on your forecasted-sunny parade.
Can Conley indentify a source of forecasts he thinks will more reliably
predict the next presidential election results? If so, I'll bet him $100
that the IEM forecast will do at least as well. If not, he's just
complaining about the rain.
Robin Hanson rhanson@gmu.edu http://hanson.gmu.edu
Asst. Prof. Economics, George Mason University
MSN 1D3, Carow Hall, Fairfax VA 22030-4444
703-993-2326 FAX: 703-993-2323
This archive was generated by hypermail 2b30 : Mon May 28 2001 - 09:50:30 MDT