Bayes' theorem
The rule for updating the probability of a hypothesis given new data: the posterior is proportional to the likelihood of the data under the hypothesis times the prior probability.
As defined in 200 | Solo: The Philosophy of the Multiverse
Where it comes up · 10
- 180 | Camilla Pang on Instructions for Being Human3 claims
- 6 | Liv Boeree on Poker, Aliens, and Thinking in Probabilities3 claims
- 200 | Solo: The Philosophy of the Multiverse2 claims
- 216 | John Allen Paulos on Numbers, Narratives, and Numeracy2 claims
- Mindscape Ask Me Anything, Sean Carroll | September 20262 claims
- Arnold Kling on the Economics of Health Care and the Crisis of Abundance 11/5/20071 claim
- 54 | Indre Viskontas on Music and the Brain1 claim
- AMA | August 20221 claim
and 2 more
Most important claims · 10 of 17Search all claims for “Bayes' theorem” →
- Because of Bayes' theorem, a test for a rare disease (1-in-1000 prevalence) with a 5% false-positive rate yields a positive result that means only about a 1-in-51 (under 2%) chance of actually having the disease — not 95% — so screening for very rare conditions can be a waste even with a 'good' test.Arnold Kling on the Economics of Health Care and the Crisis of Abundance 11/5/2007
- Concepts in probability and statistics are refinements or distillations of hazy everyday notions: natural language already contains words for central tendency (mean/median/mode) and variance (far out, disparate), and people have been 'speaking probability' all their lives, just with a very bad accent.216 | John Allen Paulos on Numbers, Narratives, and Numeracy
- The questioner asks whether the host assigns explicit probabilities and updates them via Bayes' theorem, noting that a 70 percent forecast is judged wrong when the event fails, which makes percentage framing risky.Mindscape Ask Me Anything, Sean Carroll | September 2026
- Bayesian analysis is updating your model of the world based on new information, shifting your beliefs by an amount proportional to the strength of the evidence—as when seeing a tree with purple leaves shifts you away from the belief that all leaves are green—and Bayes' theorem provides the mathematically correct, rational way to do this updating.6 | Liv Boeree on Poker, Aliens, and Thinking in Probabilities
- Reasoning in a multiverse requires two different kinds of credence: the standard scientific credence over which theory is correct (is there a cosmological multiverse, is many-worlds right), and a distinct credence about who we are within a scenario that contains many observers (self-locating or indexical uncertainty), and the latter is the genuinely novel philosophical problem.200 | Solo: The Philosophy of the Multiverse
- Applying Bayes' rule to cosmological scenarios is stuck on the likelihood function because the only data is 'I exist'; it is unclear whether to ask the probability that any observers exist, observers like me, or exactly me, and whether one's own existence is genuinely new evidence or old evidence already baked into the priors (the problem of old evidence), making the update ambiguous.200 | Solo: The Philosophy of the Multiverse
- If you pick one of two coins (one two-headed, one fair) and flip three heads in a row, Bayes' theorem shows the probability you picked the two-headed coin rises from 1/2 to 8/9, formalizing the common-sense intuition that you probably have the two-headed coin.216 | John Allen Paulos on Numbers, Narratives, and Numeracy
- Bayes' theorem can legitimately be applied to historical questions like whether a figure such as Jesus existed, because historical claims are not simply true or false to us but carry uncertainty that is properly represented as probabilities updated by evidence; treating history probabilistically is a feature, not a misuse, of Bayesian reasoning.AMA | March 2024
- Bayesian reasoning is useful for contextualizing whether an event will happen based on what preceded it, but it is limited because it assumes determinism rests only on what has happened before; modeling chaotic intelligent systems with it will hit a wall quickly, which is why constructor theory is appealing for projecting what can and cannot physically happen rather than only what already has.180 | Camilla Pang on Instructions for Being Human
- Although she doesn't compute likelihood ratios consciously, our brains are fundamentally Bayesian machines that update beliefs on evidence naturally without our realizing it, which Boeree treats as a kind of psychological law of the world we live in.6 | Liv Boeree on Poker, Aliens, and Thinking in Probabilities