Statistical inference and large-scale multiple testing for high-dimensional regression models

Cai, Tommaso; Guo, Zijian; Yin, Xia

doi:10.1007/s11749-023-00870-1

Cited by 3 publications

(1 citation statement)

References 95 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cox regression. See Cai, Guo and Xia (2023) for a thorough review of debiasing methods for high-dimensional inference.…”

Section: Introductionmentioning

confidence: 99%

Linear Hypothesis Testing for High Dimensional Tobit Models

Jacobson,

Zou

2026

STAT SINICA

View full text Add to dashboard Cite

Few methods have been developed for conducting statistical inference in high-dimensional left-censored regression. Among the methods that do exist, none are flexible enough to test general linear hypotheses-that is, all hypotheses of the form H0 : Cβ * M = t. To fill this gap, we introduce partial penalized Tobit tests for testing general linear hypotheses in high-dimensional left-censored data. In particular, we develop partial penalized Wald, score, and likelihood ratio tests for high-dimensional Tobit models. We derive approximate distributions for the partial penalized Tobit test statistics under the null hypothesis and local alternatives in an ultra high-dimensional setting, finding that the tests achieve their nominal size asymptotically and that they are approximately equivalent for large n. In addition, we derive the tests' approximate power in this setting. We propose an alternating direction method of multipliers algorithm to compute the partial penalized test statistics. Through an extensive empirical study, we show that the partial penalized Tobit tests achieve their nominal size and that they are consistent in a finite sample setting. As an application, we analyze data from Statistica Sinica: Newly accepted Paper (accepted author-version subject to English editing)the AIDS Clinical Trials Group, using our partial penalized Tobit tests to test whether certain HIV mutations are significant predictors of HIV viral load.

show abstract

“…Cox regression. See Cai, Guo and Xia (2023) for a thorough review of debiasing methods for high-dimensional inference.…”

Section: Introductionmentioning

confidence: 99%