uskomusväliarviot
Uskomusväliarviot, known in English as credibility intervals or belief intervals, are a key concept in Bayesian statistics. They represent a range of plausible values for an unknown parameter, reflecting the degree of belief or uncertainty about that parameter's true value. Unlike frequentist confidence intervals, which are interpreted based on repeated sampling, credibility intervals are directly interpreted in terms of probability. If a 95% credibility interval for a parameter is [2.5, 4.0], it means there is a 95% probability that the true value of the parameter lies within this range, given the observed data and the prior beliefs.
The construction of credibility intervals is based on the posterior distribution of the parameter. After a