A Bayesian two-stage spatially dependent variable selection model for space–time health data

Jungsoon Choi, Andrew B. Lawson

Research output: Contribution to journalArticleResearchpeer-review

1 Citation (Scopus)

Abstract

In space–time epidemiological modeling, most studies have considered the overall variations in relative risk to better estimate the effects of risk factors on health outcomes. However, the associations between risk factors and health outcomes may vary across space and time. Especially, the temporal patterns of the covariate effects may depend on space. Thus, we propose a Bayesian two-stage spatially dependent variable selection approach for space–time health data to determine the spatially varying subsets of regression coefficients with common temporal dependence. The two-stage structure allows reduction of the spatial confounding bias in the estimates of the regression coefficients. A simulation study is conducted to examine the performance of the proposed two-stage model. We apply the proposed model to the number of inpatients with lung cancer in 159 counties of Georgia, USA.

Original languageEnglish
Pages (from-to)2570-2582
Number of pages13
JournalStatistical Methods in Medical Research
Volume28
Issue number9
DOIs
StatePublished - 2019 Sep 1

Fingerprint

Selection Model
Variable Selection
Health
Space-time
Risk Factors
Regression Coefficient
Dependent
Two-stage Model
Stage Structure
Relative Risk
Confounding
Lung Cancer
Estimate
Covariates
Inpatients
Lung Neoplasms
Simulation Study
Vary
Subset
Modeling

Keywords

  • Bayesian spatial variable selection
  • Spatial confounding problem
  • spatial random component

Cite this

@article{9e9867fca1334a5487ab253528b5378c,
title = "A Bayesian two-stage spatially dependent variable selection model for space–time health data",
abstract = "In space–time epidemiological modeling, most studies have considered the overall variations in relative risk to better estimate the effects of risk factors on health outcomes. However, the associations between risk factors and health outcomes may vary across space and time. Especially, the temporal patterns of the covariate effects may depend on space. Thus, we propose a Bayesian two-stage spatially dependent variable selection approach for space–time health data to determine the spatially varying subsets of regression coefficients with common temporal dependence. The two-stage structure allows reduction of the spatial confounding bias in the estimates of the regression coefficients. A simulation study is conducted to examine the performance of the proposed two-stage model. We apply the proposed model to the number of inpatients with lung cancer in 159 counties of Georgia, USA.",
keywords = "Bayesian spatial variable selection, Spatial confounding problem, spatial random component",
author = "Jungsoon Choi and Lawson, {Andrew B.}",
year = "2019",
month = "9",
day = "1",
doi = "10.1177/0962280218767980",
language = "English",
volume = "28",
pages = "2570--2582",
journal = "Statistical Methods in Medical Research",
issn = "0962-2802",
number = "9",

}

A Bayesian two-stage spatially dependent variable selection model for space–time health data. / Choi, Jungsoon; Lawson, Andrew B.

In: Statistical Methods in Medical Research, Vol. 28, No. 9, 01.09.2019, p. 2570-2582.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A Bayesian two-stage spatially dependent variable selection model for space–time health data

AU - Choi, Jungsoon

AU - Lawson, Andrew B.

PY - 2019/9/1

Y1 - 2019/9/1

N2 - In space–time epidemiological modeling, most studies have considered the overall variations in relative risk to better estimate the effects of risk factors on health outcomes. However, the associations between risk factors and health outcomes may vary across space and time. Especially, the temporal patterns of the covariate effects may depend on space. Thus, we propose a Bayesian two-stage spatially dependent variable selection approach for space–time health data to determine the spatially varying subsets of regression coefficients with common temporal dependence. The two-stage structure allows reduction of the spatial confounding bias in the estimates of the regression coefficients. A simulation study is conducted to examine the performance of the proposed two-stage model. We apply the proposed model to the number of inpatients with lung cancer in 159 counties of Georgia, USA.

AB - In space–time epidemiological modeling, most studies have considered the overall variations in relative risk to better estimate the effects of risk factors on health outcomes. However, the associations between risk factors and health outcomes may vary across space and time. Especially, the temporal patterns of the covariate effects may depend on space. Thus, we propose a Bayesian two-stage spatially dependent variable selection approach for space–time health data to determine the spatially varying subsets of regression coefficients with common temporal dependence. The two-stage structure allows reduction of the spatial confounding bias in the estimates of the regression coefficients. A simulation study is conducted to examine the performance of the proposed two-stage model. We apply the proposed model to the number of inpatients with lung cancer in 159 counties of Georgia, USA.

KW - Bayesian spatial variable selection

KW - Spatial confounding problem

KW - spatial random component

UR - http://www.scopus.com/inward/record.url?scp=85045283217&partnerID=8YFLogxK

U2 - 10.1177/0962280218767980

DO - 10.1177/0962280218767980

M3 - Article

VL - 28

SP - 2570

EP - 2582

JO - Statistical Methods in Medical Research

JF - Statistical Methods in Medical Research

SN - 0962-2802

IS - 9

ER -