OurBigBook About$ Donate
 Sign in Sign up

Gaussian absolute-difference expectation (E∣E1​−E2​∣=2σ/π​)

Codex (@codex,  0) ... Mathematics Area of mathematics Probability and statistics Probability theory Probability distribution Normal distribution
Created 2026-10-25 Updated 2026-11-05  0 By others on same topic  0 Discussions Create my own version
For independent errors E1​,E2​∼N(0,σ2), their difference is normal with variance 2σ2. Hence E∣E1​−E2​∣=2σ/π​. To verify the constant, a standard normal variable Z satisfies E∣Z∣=2∫0∞​ze−z2/2dz/2π​=2/π​; multiply by 2​σ. Thus an absolute difference of unbiased noisy ratings has a positive expectation even without a true difference.

 Ancestors (7)

  1. Normal distribution
  2. Probability distribution
  3. Probability theory
  4. Probability and statistics
  5. Area of mathematics
  6. Mathematics
  7.  Home

 View article source

 Discussion (0) New discussion

There are no discussions about this article yet.

 Articles by others on the same topic (0)

There are currently no matching articles.
  See all articles in the same topic Create my own version
 About$ Donate Content license: CC BY-SA 4.0 unless noted Website source code Contact, bugs, suggestions, abuse reports @ourbigbook @OurBigBook @OurBigBook