The representativeness heuristic is the tendency to judge the likelihood of an event by how closely it matches a prototype or stereotype, rather than by base rates or other statistical information.

If a quiet, orderly person who likes poetry is described, many people rate the probability that the person is a librarian higher than the probability that the person is a salesperson, even though salespeople greatly outnumber librarians. The description fits the librarian prototype more closely, so representativeness overrides the base-rate information. The heuristic is efficient and often accurate, yet it produces systematic errors when stereotypes are strong and base rates are ignored.

Kahneman and Tversky identified the bias in a series of classic studies. It contributes to conjunction fallacies, misjudgments of randomness, and the neglect of regression to the mean. Awareness of the heuristic can improve judgment, but the pull of the prototype remains powerful even among statistically sophisticated people.

When similarity to a mental image outweighs actual frequency, the representativeness heuristic is at work.