https://en.wikipedia.org/wiki/Empirical_Bayes_method

prior distribution is estimated from the data

데이터로부터 추정되는 사전분포

standard Bayesian methods : prior distribution is fixed before any data are observed

표준 베이즈 방법에서는 데이터를 관찰하기 전에 사전분포가 정해짐

Despite this difference in perspective, empirical Bayes may be viewed as an approximation to a fully Bayesian treatment of a hierarchical model wherein the parameters at the highest level of the hierarchy are set to their most likely values, instead of being integrated out. Empirical Bayes, also known as maximum marginal likelihood,[1] represents one approach for setting hyperparameters.