principle of difference

statistics

What

a.k.a: principle of sufficient reason

It states that

 In the absence of any relevant evidence, agents should distribute their credence (or “degrees of belief”) equally among all the possible outcomes under consideration

It basically means: If no relevant information -> assigning equal probability to all possible outcomes.

In Bayesian statistics, it gives the simplest non-informative prior

• $P(H)$ : the prior probability - the prior knowledge (the estimate probability) of the hypothesis $H$ before any more evidence.

Link to original

In frequentist statistics, it is meaningless.

• because in frequentist statistics, probabilities are relative frequencies rather than degrees of belief in uncertain propositions.