Skip to content

Latest commit

 

History

History
23 lines (17 loc) · 728 Bytes

File metadata and controls

23 lines (17 loc) · 728 Bytes

Bayes' Theorem

  • Hypothesis: $H$

  • Prior probability: $P(H)$

  • Evidence: $E$

  • Likelihood: $P(E|H)$

  • Posterior probability: $P(H|E)$

  • Bayes' theorem:

    $$\text{Posterior}=\text{Prior}\times\text{Likelihood}\div\text{Evidence}$$

    $$P(H|E) = {P(H)P(E|H) \over P(E)} = {P(H)P(E|H) \over P(H)P(E|H)+P(\lnot H)P(E|\lnot H)}$$

Bayes theorem, the geometry of changing beliefs - YouTube

  • Hypothesis: One is a librarian

  • Prior probability: $10\over 210$

  • Evidence: One fits the description, $4+20 \over 210$

  • Likelihood: ${4\over 10}$

  • Posterior probability: ${4 \over 4+20}$

  • Bayes' theorem:

    $${4\over 4+20}={{10\over 210}\times{4\over 10}\over {4+20\over 210}}$$