Stability via resampling: statistical problems beyond the real line

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Soloff, Jake A., Barber, Rina Foygel, Willett, Rebecca
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914811030274048
author Soloff, Jake A.
Barber, Rina Foygel
Willett, Rebecca
author_facet Soloff, Jake A.
Barber, Rina Foygel
Willett, Rebecca
contents Model averaging techniques based on resampling methods (such as bootstrapping or subsampling) have been utilized across many areas of statistics, often with the explicit goal of promoting stability in the resulting output. We provide a general, finite-sample theoretical result guaranteeing the stability of bagging when applied to algorithms that return outputs in a general space, so that the output is not necessarily a real-valued -- for example, an algorithm that estimates a vector of weights or a density function. We empirically assess the stability of bagging on synthetic and real-world data for a range of problem settings, including causal inference, nonparametric regression, and Bayesian model selection.
format Preprint
id arxiv_https___arxiv_org_abs_2405_09511
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Stability via resampling: statistical problems beyond the real line
Soloff, Jake A.
Barber, Rina Foygel
Willett, Rebecca
Statistics Theory
Model averaging techniques based on resampling methods (such as bootstrapping or subsampling) have been utilized across many areas of statistics, often with the explicit goal of promoting stability in the resulting output. We provide a general, finite-sample theoretical result guaranteeing the stability of bagging when applied to algorithms that return outputs in a general space, so that the output is not necessarily a real-valued -- for example, an algorithm that estimates a vector of weights or a density function. We empirically assess the stability of bagging on synthetic and real-world data for a range of problem settings, including causal inference, nonparametric regression, and Bayesian model selection.
title Stability via resampling: statistical problems beyond the real line
topic Statistics Theory
url https://arxiv.org/abs/2405.09511