Skip to content

Instantly share code, notes, and snippets.

@tristanpendergrass

tristanpendergrass/gist:f64f51c3dc2e3dc83d31

Created November 27, 2014 16:34
Show Gist options
  • Save tristanpendergrass/f64f51c3dc2e3dc83d31 to your computer and use it in GitHub Desktop.
Save tristanpendergrass/f64f51c3dc2e3dc83d31 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
gistfile1.txt
Scenario 1:
Predictor says there is an x% chance of a coin A coming up heads.
We flip it once and see the result.
At this point what can we say about the "accuracy" of the predictor?
Scenario 2:
Predictor says there is an x% chance of coin B coming up heads.
We flip coin B many times and see all the results.
At this point what can we say about the "accuracy" of the predictor?
Scenario 3:
Predictor says there is an x% chance of coin C coming up heads, y% for coin D, and z% for coin E (they are all different coins with possibly different weightings).
We flip all the coins once and see all the results.
At this point what can we say about the "accuracy" of the predictor?
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment