Bayesian interval estimate analogous to a confidence interval
A credible interval is the Bayesian equivalent of a confidence interval, giving the range within which the true effect most likely lies given the data and prior assumptions used in the model. Unlike a frequentist CI, it has a direct probabilistic interpretation (e.g. 95% probability the true value lies in this range), but its width and location can depend on the chosen prior. A CrI that excludes zero, as reported here for cluster and intra-set rest-redistribution sets, supports a real effect distinct from chance.
This guide was auto-drafted and is pending editorial review.