Scholion.ai

The Interpretation of Improper Prior Distributions as Limits of Data Dependent Proper Prior Distributions

Hirotugu Akaike

Journal of the Royal Statistical Society: Series B (Statistical Methodology) · 1980 · Volume 42 · Issue 1

DOI: 10.1111/j.2517-6161.1980.tb01099.x

Abstract

By using examples the difficulty of interpreting an improper prior distribution as a limit of some proper prior distributions is demonstrated. It is shown that an improper prior distribution can often be more adequately described as a limit of some data adaptive proper prior distributions.

Keywords

bayes procedure, improper prior distribution, data adaptive prior distribution, marginalization paradox

Enable JavaScript for citation tools and additional paper interactions.