Nonuniformity of P-values Can Occur Early in Diverging Dimensions

Authors: Yingying Fan, Emre Demirkaya, Jinchi Lv

JMLR 2019 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our theoretical characterizations are confirmed by simulation studies. ... Section 4 presents several simulation examples verifying the theoretical phenomenon.
Researcher Affiliation Academia Yingying Fan EMAIL Data Sciences and Operations Department University of Southern California Los Angeles, CA 90089, USA; Emre Demirkaya EMAIL Business Analytics & Statistics The University of Tennessee, Knoxville Knoxville, TN 37996-4140, USA; Jinchi Lv EMAIL Data Sciences and Operations Department University of Southern California Los Angeles, CA 90089, USA
Pseudocode No The paper describes theoretical proofs and derivations. There are no explicit pseudocode or algorithm blocks presented.
Open Source Code No The paper does not contain any statements or links indicating that source code for the described methodology is publicly available.
Open Datasets No The paper uses simulated data for its numerical studies, as indicated by "we generate the n p design matrix X" and "each yi has Bernoulli distribution". It does not refer to any external, publicly available datasets.
Dataset Splits No The numerical studies involve generating synthetic data based on specified distributions and parameters, rather than using pre-existing datasets with defined train/test/validation splits. Therefore, dataset split information is not applicable in the traditional sense for this paper's methodology.
Hardware Specification No The paper describes simulation experiments but does not provide any specific details about the hardware (e.g., GPU, CPU models, memory) used to run these simulations.
Software Dependencies No The paper does not mention any specific software or library names with version numbers that were used for the simulations or analyses.
Experiment Setup Yes To examine the asymptotic results we set the sample size n = 1000. In each example, we consider a spectrum of dimensionality p with varying rate of growth with sample size n. ... We set p = [nα0] with α0 in the grid {2/3 4δ, ..., 2/3 + 4δ, (log(n) log(2))/ log(n)} for δ = 0.05. For example 3, we pick s signals uniformly at random among all but the first components, where a random half of them are chosen as 3 and the other half are set as 3.