Conference Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 524 - Recent Advances in Methods for Genomic Data Analysis
Type: Contributed
Date/Time: Thursday, August 11, 2022 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistics in Genomics and Genetics
Abstract #323083
Title: High-Dimensional Mean Vector Test for One-Sided Hypothesis
Author(s): Rongrong Wang* and Deepak Nag Ayyala and Santu Ghosh
Companies: Division of Biostatistics and Data Science Medical College of Georgia Augusta University ? and Division of Biostatistics and Data Science Medical College of Georgia Augusta University ? and Division of Biostatistics and Data Science Medical College of Georgia Augusta University ?
Keywords: Multivariate one-sided test, High-dimensional data, Generalized max-component test
Abstract:

The advancement of data acquisition technologies and computing resources have greatly facilitated the analysis of massive data sets in various fields. A unique characteristic of these data sets contains a large number of features but a small number of subjects, known as high-dimensional data. These data demand new statistical methods to enhance scientific knowledge. One of the important statistical inferences is mean vector testing. A lot of efficient statistical methods have been developed for performing the two-sided mean vector test. The one-sided high-dimensional mean vector test has been received limited attention. One relevant application could be identifying significant upregulated or downregulated gene set from the preselected gene sets. This work develops a procedure for a one-sided high-dimensional mean vector test, known as the generalized max-component test (GMCT). We study the asymptotic distribution of GMCT statistic. The GMCT is robust to heteroscedasticity in the component variances and is computationally efficient. The finite sample performance of the proposed test statistic is evaluated, and it achieves competitive rates for type-I error and power.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2022 program