Wrong Priors

TL;DR

This paper argues that in statistical practice, the choice of priors is crucial, demonstrating that many commonly used priors are incorrect and can lead to misleading results, through illustrative examples.

Contribution

It highlights the importance of selecting appropriate priors and shows that many standard priors are fundamentally wrong, impacting statistical inference.

Findings

Many standard priors are incorrect and lead to misleading inferences

Illustrative examples demonstrate the prevalence of wrong priors

Choosing the right prior is essential for valid statistical analysis

Abstract

All priors are not created equal. There are right and there are wrong priors. That is the main conclusion of this contribution. I use, a cooked-up example designed to create drama, and a typical textbook example to show the pervasiveness of wrong priors in standard statistical practice.