Assumption-Lean Honest Inference for $Z$-functionals

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chang, Woonyoung, Kuchibhotla, Arun Kumar
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916835159441408
author Chang, Woonyoung
Kuchibhotla, Arun Kumar
author_facet Chang, Woonyoung
Kuchibhotla, Arun Kumar
contents We develop a general assumption-lean framework for constructing uniformly valid confidence sets for functionals defined by moment equalities, referred to as $Z$-functionals. Our approach combines self-normalized statistics with a test inversion principle, enabling honest inference under mild regularity conditions and without explicit variance estimation. To enhance geometric tractability, we propose novel split-normalized and Gateaux-normalized statistics that yield computationally feasible and interpretable confidence sets. A central contribution of this work is a comprehensive non-asymptotic width analysis: we derive high-probability upper bounds on the diameter of the proposed confidence sets, and quantify their proximity to Wald intervals under minimal assumptions. Applications to high-dimensional non-sparse linear and generalized linear regression demonstrate that our procedures achieve valid coverage and near-optimal rate of convergence for the width/diameter, while the classical methods including Wald and bootstrap fail.
format Preprint
id arxiv_https___arxiv_org_abs_2407_12278
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Assumption-Lean Honest Inference for $Z$-functionals
Chang, Woonyoung
Kuchibhotla, Arun Kumar
Statistics Theory
We develop a general assumption-lean framework for constructing uniformly valid confidence sets for functionals defined by moment equalities, referred to as $Z$-functionals. Our approach combines self-normalized statistics with a test inversion principle, enabling honest inference under mild regularity conditions and without explicit variance estimation. To enhance geometric tractability, we propose novel split-normalized and Gateaux-normalized statistics that yield computationally feasible and interpretable confidence sets. A central contribution of this work is a comprehensive non-asymptotic width analysis: we derive high-probability upper bounds on the diameter of the proposed confidence sets, and quantify their proximity to Wald intervals under minimal assumptions. Applications to high-dimensional non-sparse linear and generalized linear regression demonstrate that our procedures achieve valid coverage and near-optimal rate of convergence for the width/diameter, while the classical methods including Wald and bootstrap fail.
title Assumption-Lean Honest Inference for $Z$-functionals
topic Statistics Theory
url https://arxiv.org/abs/2407.12278