Two interesting follow-ups to the discussion about presidential election forecasting models — e.g., Nate Silver, me.
First, Lynn Vavreck:
bq. Election forecasts based on economic indicators are valuable not for their point-estimates, but for their overall predictions about which party is likely to win the election. They are valuable because they tell candidates what kinds of campaigns to run and they help analysts understand a priori, in a systematic manner, why some strategies are winning ones and others are not.
And here is Jay Ulfelder, concluding an interesting discussion of forecasting rare events like state-sponsored mass violence.
bq. The broader point is that, when trying to forecast rare events, we shouldn’t get too hung up on the exact values of the predicted probabilities. The model we’re striving for here isn’t an actuarial table that allows us to allocate our dollars and attention as efficiently as possible. Even if policy and advocacy worked that way–and they don’t–the statistics won’t allow it.
bq. A more useful model, I think, is light on your dashboard that tells you you’re running low on fuel. When that light comes on, you don’t know how far you can drive before you’ll run out of gas, but you do know that you’d better start worrying about refilling soon. The light directs your attention to a potential problem you probably weren’t thinking about a few moments earlier. A reasonably well-calibrated statistical model of rare political events should do the same thing for analysts and other concerned observers, whose attention usually doesn’t get redirected until the engine is already sputtering.
I agree with the emphasis here: don’t get too bogged down in the precise predictions. Use the forecast as a signal that some outcome is more likely.