SIGHR: Side information guided high-dimensional regression

In this work, we develop a novel Bayesian regression framework that can be used to complete variable selection in high dimensional settings. Unlike existing techniques, the proposed approach can leverage side information to inform about the sparsity structure of the regression coefficients. This is...

Full description

Saved in:
Bibliographic Details
Published in:Statistical methods in medical research 2023-11, Vol.32 (11), p.2270-2282
Main Authors: Yang, Yuan, McMahan, Christopher S, Wang, Yu-Bo, Baurley, James W, Park, Sung-Shim
Format: Article
Language:English
Subjects:
Algorithms
Bayes Theorem
Bayesian analysis
Biological markers
Biomarkers
Data augmentation
Feature selection
Genetic Markers
Markov analysis
Markov Chains
Metabolites
Monte Carlo simulation
Nicotine
Regression analysis
Regression coefficients
Regression models
Smoking cessation
Sparsity
Statistical analysis
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this work, we develop a novel Bayesian regression framework that can be used to complete variable selection in high dimensional settings. Unlike existing techniques, the proposed approach can leverage side information to inform about the sparsity structure of the regression coefficients. This is accomplished by replacing the usual inclusion probability in the spike and slab prior with a binary regression model which assimilates this extra source of information. To facilitate model fitting, a computationally efficient and easy to implement Markov chain Monte Carlo posterior sampling algorithm is developed via carefully chosen priors and data augmentation steps. The finite sample performance of our methodology is assessed through numerical simulations, and we further illustrate our approach by using it to identify genetic markers associated with the nicotine metabolite ratio; a key biological marker associated with nicotine dependence and smoking cessation treatment.
ISSN:0962-2802
1477-0334
DOI:10.1177/09622802231206475