American football has some properties that make it useful for practicing making predictions:

  • A game consists of a sequence of discrete plays with well-defined outcomes
  • The plays are fast enough that you get quick feedback on each prediction, and there are enough plays in a game that you can make enough predictions to see how well calibrated you are
  • You go into each prediction with at least some information about what you're predicting

I've created a forecasting practice exercise that you can do while watching a game, either on paper or using this spreadsheet.

For those with no idea how football works, there's a decent basic intro here.


Before each down, write down the probability that the current frame will succeed (result in a first down or a touchdown). Once the frame finishes, write the outcome next to your prediction. Repeat.

Optionally, on the special plays (kickoff, punt, field goal attempt, and 2 point attempt), predict whether that play will succeed, and then write down the outcome.

For a field goal or 2 point attempt, success or failure is clear: the team attempting to score either does or doesn't.

For punts and kickoffs, there isn't a sharp dividing line between success and failure, but one definition you can use is that the kick is "successful" if the result is better for the kicking team than a touchback.

1 comments, sorted by Click to highlight new comments since: Today at 11:34 PM
New Comment

I think to this approach to be beneficial the predictions would need to be much more narrowly defined that described here. Things along the lines or Offence will rush or pass or even more fine grained such as rush to short side of the field with tackle pulling, rush with sweep and back up of a pitchback. For passing some idea about receiver type -- wide or one of the backs -- as well as how deep. For punts and kick-offs perhaps things like what receiver is targeted or take away option to return, or for punts various fake play scenario.

If we just say "succeed" I'm not sure what we're really testing as we don't seem to be saying anything about the play to be executed so seems like the success/fail results will have a lot of noise in them.

I do agree that sports offers a great environment for such efforts for the reasons you've listed. So perhaps just adding clarifying points here.

New to LessWrong?