Predictive performance of power posteriors

Bibliographic Details
Title: Predictive performance of power posteriors
Authors: McLatchie, Yann, Fong, Edwin, Frazier, David T., Knoblauch, Jeremias
Publication Year: 2024
Collection: Mathematics
Statistics
Subject Terms: Mathematics - Statistics Theory
More Details: We analyse the impact of using tempered likelihoods in the production of posterior predictions. Our findings reveal that once the sample size is at least moderately large and the temperature is not too small, then likelihood tempering has virtually no impact on the resulting posterior predictions.
Comment: 7 (+14 supplementary) pages (excluding references); 3 (+4 supplementary) figures
Document Type: Working Paper
Access URL: http://arxiv.org/abs/2408.08806
Accession Number: edsarx.2408.08806
Database: arXiv
More Details
Description not available.