A marginal structural model approach to analyse work-related injuries: An example using data from the health and retirement study

Navneet Kaur Baidwan, Susan G Gerberich, Hyun Kim, Andrew Ryan, Timothy R Church, Benjamin Capistrant

Research output: Contribution to journalArticle

Abstract

Background: Biases may exist in the limited longitudinal data focusing on work-related injuries among the ageing workforce. Standard statistical techniques may not provide valid estimates when the data are time-varying and when prior exposures and outcomes may influence future outcomes. This research effort uses marginal structural models (MSMs), a class of causal models rarely applied for injury epidemiology research to analyse work-related injuries. Methods: 7212 working US adults aged ≥50 years, obtained from the Health and Retirement Study sample in the year 2004 formed the study cohort that was followed until 2014. The analyses compared estimates measuring the associations between physical work requirements and work-related injuries using MSMs and a traditional regression model. The weights used in the MSMs, besides accounting for time-varying exposures, also accounted for the recurrent nature of injuries. Results: The results were consistent with regard to directionality between the two models. However, the effect estimate was greater when the same data were analysed using MSMs, built without the restriction for complete case analyses. Conclusions: MSMs can be particularly useful for observational data, especially with the inclusion of recurrent outcomes as these can be incorporated in the weights themselves.

Original languageEnglish (US)
JournalInjury Prevention
DOIs
StatePublished - Jan 1 2019

Fingerprint

Retirement
Structural Models
Health
Wounds and Injuries
Weights and Measures
Research
Epidemiology
Cohort Studies

Keywords

  • inverse probability weighting
  • marginal structural models
  • time-varying data
  • work-related injuries

PubMed: MeSH publication types

  • Journal Article

Cite this

@article{2b654069f0534b91a1a552d97b350472,
title = "A marginal structural model approach to analyse work-related injuries: An example using data from the health and retirement study",
abstract = "Background: Biases may exist in the limited longitudinal data focusing on work-related injuries among the ageing workforce. Standard statistical techniques may not provide valid estimates when the data are time-varying and when prior exposures and outcomes may influence future outcomes. This research effort uses marginal structural models (MSMs), a class of causal models rarely applied for injury epidemiology research to analyse work-related injuries. Methods: 7212 working US adults aged ≥50 years, obtained from the Health and Retirement Study sample in the year 2004 formed the study cohort that was followed until 2014. The analyses compared estimates measuring the associations between physical work requirements and work-related injuries using MSMs and a traditional regression model. The weights used in the MSMs, besides accounting for time-varying exposures, also accounted for the recurrent nature of injuries. Results: The results were consistent with regard to directionality between the two models. However, the effect estimate was greater when the same data were analysed using MSMs, built without the restriction for complete case analyses. Conclusions: MSMs can be particularly useful for observational data, especially with the inclusion of recurrent outcomes as these can be incorporated in the weights themselves.",
keywords = "inverse probability weighting, marginal structural models, time-varying data, work-related injuries",
author = "Baidwan, {Navneet Kaur} and Gerberich, {Susan G} and Hyun Kim and Andrew Ryan and Church, {Timothy R} and Benjamin Capistrant",
year = "2019",
month = "1",
day = "1",
doi = "10.1136/injuryprev-2018-043124",
language = "English (US)",
journal = "Injury Prevention",
issn = "1353-8047",
publisher = "BMJ Publishing Group",

}

TY - JOUR

T1 - A marginal structural model approach to analyse work-related injuries

T2 - An example using data from the health and retirement study

AU - Baidwan, Navneet Kaur

AU - Gerberich, Susan G

AU - Kim, Hyun

AU - Ryan, Andrew

AU - Church, Timothy R

AU - Capistrant, Benjamin

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Background: Biases may exist in the limited longitudinal data focusing on work-related injuries among the ageing workforce. Standard statistical techniques may not provide valid estimates when the data are time-varying and when prior exposures and outcomes may influence future outcomes. This research effort uses marginal structural models (MSMs), a class of causal models rarely applied for injury epidemiology research to analyse work-related injuries. Methods: 7212 working US adults aged ≥50 years, obtained from the Health and Retirement Study sample in the year 2004 formed the study cohort that was followed until 2014. The analyses compared estimates measuring the associations between physical work requirements and work-related injuries using MSMs and a traditional regression model. The weights used in the MSMs, besides accounting for time-varying exposures, also accounted for the recurrent nature of injuries. Results: The results were consistent with regard to directionality between the two models. However, the effect estimate was greater when the same data were analysed using MSMs, built without the restriction for complete case analyses. Conclusions: MSMs can be particularly useful for observational data, especially with the inclusion of recurrent outcomes as these can be incorporated in the weights themselves.

AB - Background: Biases may exist in the limited longitudinal data focusing on work-related injuries among the ageing workforce. Standard statistical techniques may not provide valid estimates when the data are time-varying and when prior exposures and outcomes may influence future outcomes. This research effort uses marginal structural models (MSMs), a class of causal models rarely applied for injury epidemiology research to analyse work-related injuries. Methods: 7212 working US adults aged ≥50 years, obtained from the Health and Retirement Study sample in the year 2004 formed the study cohort that was followed until 2014. The analyses compared estimates measuring the associations between physical work requirements and work-related injuries using MSMs and a traditional regression model. The weights used in the MSMs, besides accounting for time-varying exposures, also accounted for the recurrent nature of injuries. Results: The results were consistent with regard to directionality between the two models. However, the effect estimate was greater when the same data were analysed using MSMs, built without the restriction for complete case analyses. Conclusions: MSMs can be particularly useful for observational data, especially with the inclusion of recurrent outcomes as these can be incorporated in the weights themselves.

KW - inverse probability weighting

KW - marginal structural models

KW - time-varying data

KW - work-related injuries

UR - http://www.scopus.com/inward/record.url?scp=85065322898&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065322898&partnerID=8YFLogxK

U2 - 10.1136/injuryprev-2018-043124

DO - 10.1136/injuryprev-2018-043124

M3 - Article

C2 - 31018941

AN - SCOPUS:85065322898

JO - Injury Prevention

JF - Injury Prevention

SN - 1353-8047

ER -