Sparse principal component based high-dimensional mediation analysis

Research output: Contribution to journalArticle

Abstract

Causal mediation analysis aims to quantify the intermediate effect of a mediator on the causal pathway from treatment to outcome. When dealing with multiple mediators, which are potentially causally dependent, the possible decomposition of pathway effects grows exponentially with the number of mediators. An existing approach incorporated the principal component analysis (PCA) to address this challenge based on the fact that the transformed mediators are conditionally independent given the orthogonality of the principal components (PCs). However, the transformed mediator PCs, which are linear combinations of original mediators, can be difficult to interpret. A sparse high-dimensional mediation analysis approach is proposed which adopts the sparse PCA method to the mediation setting. The proposed approach is applied to a task-based functional magnetic resonance imaging study, illustrating its ability to detect biologically meaningful results related to an identified mediator.

Original languageEnglish (US)
Article number106835
JournalComputational Statistics and Data Analysis
Volume142
DOIs
StatePublished - Feb 1 2020

Fingerprint

Mediation
Mediator
Principal Components
Principal component analysis
High-dimensional
Decomposition
Principal Component Analysis
Pathway
Functional Magnetic Resonance Imaging
Orthogonality
Linear Combination
Quantify
Decompose
Dependent
Magnetic Resonance Imaging

Keywords

  • Functional magnetic resonance imaging
  • Mediation analysis
  • Regularized regression
  • Structural equation model

ASJC Scopus subject areas

  • Statistics and Probability
  • Computational Mathematics
  • Computational Theory and Mathematics
  • Applied Mathematics

Cite this

Sparse principal component based high-dimensional mediation analysis. / Zhao, Yi; Lindquist, Martin; Caffo, Brian S.

In: Computational Statistics and Data Analysis, Vol. 142, 106835, 01.02.2020.

Research output: Contribution to journalArticle

@article{e5463e7b8cf74c9dbc48fee17a99f078,
title = "Sparse principal component based high-dimensional mediation analysis",
abstract = "Causal mediation analysis aims to quantify the intermediate effect of a mediator on the causal pathway from treatment to outcome. When dealing with multiple mediators, which are potentially causally dependent, the possible decomposition of pathway effects grows exponentially with the number of mediators. An existing approach incorporated the principal component analysis (PCA) to address this challenge based on the fact that the transformed mediators are conditionally independent given the orthogonality of the principal components (PCs). However, the transformed mediator PCs, which are linear combinations of original mediators, can be difficult to interpret. A sparse high-dimensional mediation analysis approach is proposed which adopts the sparse PCA method to the mediation setting. The proposed approach is applied to a task-based functional magnetic resonance imaging study, illustrating its ability to detect biologically meaningful results related to an identified mediator.",
keywords = "Functional magnetic resonance imaging, Mediation analysis, Regularized regression, Structural equation model",
author = "Yi Zhao and Martin Lindquist and Caffo, {Brian S}",
year = "2020",
month = "2",
day = "1",
doi = "10.1016/j.csda.2019.106835",
language = "English (US)",
volume = "142",
journal = "Computational Statistics and Data Analysis",
issn = "0167-9473",
publisher = "Elsevier",

}

TY - JOUR

T1 - Sparse principal component based high-dimensional mediation analysis

AU - Zhao, Yi

AU - Lindquist, Martin

AU - Caffo, Brian S

PY - 2020/2/1

Y1 - 2020/2/1

N2 - Causal mediation analysis aims to quantify the intermediate effect of a mediator on the causal pathway from treatment to outcome. When dealing with multiple mediators, which are potentially causally dependent, the possible decomposition of pathway effects grows exponentially with the number of mediators. An existing approach incorporated the principal component analysis (PCA) to address this challenge based on the fact that the transformed mediators are conditionally independent given the orthogonality of the principal components (PCs). However, the transformed mediator PCs, which are linear combinations of original mediators, can be difficult to interpret. A sparse high-dimensional mediation analysis approach is proposed which adopts the sparse PCA method to the mediation setting. The proposed approach is applied to a task-based functional magnetic resonance imaging study, illustrating its ability to detect biologically meaningful results related to an identified mediator.

AB - Causal mediation analysis aims to quantify the intermediate effect of a mediator on the causal pathway from treatment to outcome. When dealing with multiple mediators, which are potentially causally dependent, the possible decomposition of pathway effects grows exponentially with the number of mediators. An existing approach incorporated the principal component analysis (PCA) to address this challenge based on the fact that the transformed mediators are conditionally independent given the orthogonality of the principal components (PCs). However, the transformed mediator PCs, which are linear combinations of original mediators, can be difficult to interpret. A sparse high-dimensional mediation analysis approach is proposed which adopts the sparse PCA method to the mediation setting. The proposed approach is applied to a task-based functional magnetic resonance imaging study, illustrating its ability to detect biologically meaningful results related to an identified mediator.

KW - Functional magnetic resonance imaging

KW - Mediation analysis

KW - Regularized regression

KW - Structural equation model

UR - http://www.scopus.com/inward/record.url?scp=85071832837&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071832837&partnerID=8YFLogxK

U2 - 10.1016/j.csda.2019.106835

DO - 10.1016/j.csda.2019.106835

M3 - Article

VL - 142

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

SN - 0167-9473

M1 - 106835

ER -