Abstract:We develop a statistical inference method for generalized linear models (GLMs) in high-dimensional settings, where the number of unknown coefficients $p$ is of the same order as the sample size $n$. In this regime, constructing confidence intervals requires estimating unknown hyperparameters, such as the signal strength. However, existing estimators for the hyperparameters are not stably applicable to GLMs when $p/n$ is close to or greater than $1$, both theoretically and empirically. In this study, we develop an estimator for the hyperparameter that addresses the issue and establish an inferential framework, provided that the link function of the GLM exhibits an asymmetry property. The proposed estimator utilizes the moments of the output variable of GLMs and a convex surrogate loss. Our framework is theoretically valid even when the limit of $p/n$ exceeds $1$, ensuring the strong consistency of the hyperparameter estimator and asymptotically attaining the exact coverage probability of the confidence intervals. Our numerical experiments support these theoretical results.
From: Masaaki Imaizumi [view email]
[v1]
Sun, 28 May 2023 14:07:10 UTC (407 KB)
[v2]
Tue, 30 May 2023 02:43:31 UTC (407 KB)
[v3]
Wed, 25 Oct 2023 15:55:06 UTC (471 KB)
[v4]
Thu, 23 May 2024 11:13:26 UTC (1,478 KB)
[v5]
Tue, 25 Aug 2026 05:18:43 UTC (463 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。