Home
Portal
Grstats
Latest images
Register
Log in
grstats- Posts : 959
Join date : 2009-10-21 
AUEB Stats Seminars Online Premiere: Confidence Intervals for Nonparametric Empirical Bayes Analysis by N. Ignatiadis (Stanford)
Tue 1 Nov 2022 - 0:34
AUEB STATISTICS SEMINAR SERIES 2022
Nikolaos Ignatiadis
PhD Student, Statistics Department, Stanford University, USA
Confidence Intervals for Nonparametric Empirical Bayes Analysis
Online Premiere on AUEB-Stats youtube channel on
Wednesday 2/11/2022 at 19.00 (Greek time zone)
Youtube link: https://youtu.be/UV5zYX_xttM
ABSTRACT
In an empirical Bayes analysis, we use data from repeated sampling to imitate inferences made by an oracle Bayesian with extensive knowledge of the data-generating distribution. Existing results provide a comprehensive characterization of when and why empirical Bayes point estimates accurately recover oracle Bayes behavior. In this work, we construct flexible and practical nonparametric confidence intervals that provide asymptotic frequentist coverage of empirical Bayes estimands, such as the posterior mean and the local false sign rate. From a methodological perspective we build upon results on affine minimax estimation, and our coverage statements hold even when estimands are only partially identified or when empirical Bayes point estimates converge very slowly.
This is joint work with Stefan Wager.
Nikolaos Ignatiadis
PhD Student, Statistics Department, Stanford University, USA
Confidence Intervals for Nonparametric Empirical Bayes Analysis
Online Premiere on AUEB-Stats youtube channel on
Wednesday 2/11/2022 at 19.00 (Greek time zone)
Youtube link: https://youtu.be/UV5zYX_xttM
ABSTRACT
In an empirical Bayes analysis, we use data from repeated sampling to imitate inferences made by an oracle Bayesian with extensive knowledge of the data-generating distribution. Existing results provide a comprehensive characterization of when and why empirical Bayes point estimates accurately recover oracle Bayes behavior. In this work, we construct flexible and practical nonparametric confidence intervals that provide asymptotic frequentist coverage of empirical Bayes estimands, such as the posterior mean and the local false sign rate. From a methodological perspective we build upon results on affine minimax estimation, and our coverage statements hold even when estimands are only partially identified or when empirical Bayes point estimates converge very slowly.
This is joint work with Stefan Wager.
- AUEB STATS SEMINARS 4/5/2017: Dynamic borrowing through empirical power priors that control type I error
- AUEB Stats Seminars 24/6/2021: Nonparametric and high-dimensional functional graphical models by E. Solea
- AUEB STATS SEMINARS 21/3/2018: Learning Markov Equivalence Classes of Directed Acyclic Graphs: an Objective Bayes Approach by Prof. Guido Consonni
- AUEB Stats Seminars 8/10/2021: From here to infinity - bridging finite and Bayesian nonparametric mixture models in model-based clustering by Sylvia Frühwirth-Schnatter (WU Vienna University of Economics and Busin
- STATS AUEB Seminars 20/12/2017: Analytics within the European Business World: An AUEB Stats Graduate sharing his experiences by Panagiotis Pramangioulis (ECKART GmbH, ALTANA Group, Germany)
Permissions in this forum:
You cannot reply to topics in this forum