Saved in:
Bibliographic Details
Main Authors: Bariletto, Nicola, Flores, Bernardo, Walker, Stephen G.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.11360
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915303030521856
author Bariletto, Nicola
Flores, Bernardo
Walker, Stephen G.
author_facet Bariletto, Nicola
Flores, Bernardo
Walker, Stephen G.
contents We study Bayesian posterior consistency in parametric density models with proper priors, challenging the perception that the problem is settled. Classical results established consistency via MLE convergence under regularity and identifiability assumptions, with the latter taken for granted and rarely examined. We refocus attention on identifiability, showing that inconsistency arises only when the true distribution coincides with a weak limit of model densities in a way that violates identifiability. While such failures occur naturally in nonparametric settings, they are implausible and effectively self-inflicted in parametric models. Our analysis shows that classical regularity conditions are unnecessary: a mild strengthening of identifiability suffices to ensure consistency in parametric models, even when the MLE is inconsistent. We also demonstrate that parametric inconsistency requires carefully engineered, oscillatory model features aligned with the true distribution, which is unlikely to occur without adversarial design. Our findings also clarify the distinct mechanisms behind Bayesian and frequentist inconsistency and advocate for separate theoretical treatments.
format Preprint
id arxiv_https___arxiv_org_abs_2504_11360
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Posterior Consistency in Parametric Models via a Tighter Notion of Identifiability
Bariletto, Nicola
Flores, Bernardo
Walker, Stephen G.
Statistics Theory
62F15
G.3
We study Bayesian posterior consistency in parametric density models with proper priors, challenging the perception that the problem is settled. Classical results established consistency via MLE convergence under regularity and identifiability assumptions, with the latter taken for granted and rarely examined. We refocus attention on identifiability, showing that inconsistency arises only when the true distribution coincides with a weak limit of model densities in a way that violates identifiability. While such failures occur naturally in nonparametric settings, they are implausible and effectively self-inflicted in parametric models. Our analysis shows that classical regularity conditions are unnecessary: a mild strengthening of identifiability suffices to ensure consistency in parametric models, even when the MLE is inconsistent. We also demonstrate that parametric inconsistency requires carefully engineered, oscillatory model features aligned with the true distribution, which is unlikely to occur without adversarial design. Our findings also clarify the distinct mechanisms behind Bayesian and frequentist inconsistency and advocate for separate theoretical treatments.
title Posterior Consistency in Parametric Models via a Tighter Notion of Identifiability
topic Statistics Theory
62F15
G.3
url https://arxiv.org/abs/2504.11360