Bayesian Odds, Likelihood Ratios, and Base-Rate Traps

Free SOA Exam P (Probability) lesson in General Probability. 15 min read, ~2,208 words.

Odds form of Bayes: posterior odds = prior odds likelihood ratio. One multiplication updates a belief. Likelihood ratio:. For a test, that is sensitivity over (1 minus specificity). Odds to probability: if the odds are, then. Probability to odds:. Independent evidence multiplies: two conditionally independent positive results multiply the LR...