Statistical hypothesis test

Why do scientists disagree on how to interpret data?

Imagine you're trying to decide if a coin is fair. You flip it 100 times and get 60 heads. You want to know if this result suggests the coin is biased.

Think of Bayesian inference as updating your belief about the coin's fairness after seeing the results, while frequentist inference looks at the likelihood of getting 60 heads if the coin were truly fair.

Example

If you start with a strong belief the coin is fair (prior probability), seeing 60 heads (data) makes you less confident (posterior probability). Frequentist inference doesn't update beliefs but checks if 60 heads is unusually high for a fair coin.

Remember this

Bayesian inference involves updating beliefs with new evidence, while frequentist inference tests hypotheses without changing beliefs.

Text adapted from Wikipedia, licensed under CC BY-SA 4.0.

Related concepts

Prior probability

Why do we sometimes need to start with an educated guess before diving into new data?

Ronald Fisher

Ever wondered how scientists decide if something is truly special or just random?

Monty Hall problem

Switching wins 2/3 of the time

Glossary of logic

Ever wonder how scientists decide if their findings are just by chance or real?

Bayesian inference

Ever wondered how doctors update diagnoses as new symptoms arise?

Dark matter

Vera Rubin's galaxy rotation curves provided the strongest early evidence that most matter in the universe is invisible

Swipe through more Discover concepts

Open Pocket Polymath