Combining fixed effects and instrumental variable approaches for estimating the effect of psychosocial job quality on mental health: evidence from 13 waves of a nationally representative cohort study

Allison Milner, Zoe Aitken, Anne M Kavanagh, Anthony D. LaMontagne, Frank Pega, Dennis Petrie

Research output: Research - peer-reviewArticle

Abstract

Background Previous studies suggest that poor psychosocial job quality is a risk factor for mental health problems, but they use conventional regression analytic methods that cannot rule out reverse causation, unmeasured time-invariant confounding and reporting bias. Methods This study combines two quasi-experimental approaches to improve causal inference by better accounting for these biases: (i) linear fixed effects regression analysis and (ii) linear instrumental variable analysis. We extract 13 annual waves of national cohort data including 13 260 working-age (18–64 years) employees. The exposure variable is self-reported level of psychosocial job quality. The instruments used are two common workplace entitlements. The outcome variable is the Mental Health Inventory (MHI-5). We adjust for measured time-varying confounders. Results In the fixed effects regression analysis adjusted for time-varying confounders, a 1-point increase in psychosocial job quality is associated with a 1.28-point improvement in mental health on the MHI-5 scale (95% CI: 1.17, 1.40; P < 0.001). When the fixed effects was combined with the instrumental variable analysis, a 1-point increase psychosocial job quality is related to 1.62-point improvement on the MHI-5 scale (95% CI: −0.24, 3.48; P = 0.088). Conclusions Our quasi-experimental results provide evidence to confirm job stressors as risk factors for mental ill health using methods that improve causal inference.
LanguageEnglish
Number of pages9
JournalJournal of Public Health
DOIs
StateAccepted/In press - 23 Jun 2017

Keywords

  • fixed effect regression
  • instrumental variable analysis
  • MENTAL HEALTH
  • work

Cite this

@article{03afab5a48f7448da045dc3fd71e797e,
title = "Combining fixed effects and instrumental variable approaches for estimating the effect of psychosocial job quality on mental health: evidence from 13 waves of a nationally representative cohort study",
abstract = "Background Previous studies suggest that poor psychosocial job quality is a risk factor for mental health problems, but they use conventional regression analytic methods that cannot rule out reverse causation, unmeasured time-invariant confounding and reporting bias. Methods This study combines two quasi-experimental approaches to improve causal inference by better accounting for these biases: (i) linear fixed effects regression analysis and (ii) linear instrumental variable analysis. We extract 13 annual waves of national cohort data including 13 260 working-age (18–64 years) employees. The exposure variable is self-reported level of psychosocial job quality. The instruments used are two common workplace entitlements. The outcome variable is the Mental Health Inventory (MHI-5). We adjust for measured time-varying confounders. Results In the fixed effects regression analysis adjusted for time-varying confounders, a 1-point increase in psychosocial job quality is associated with a 1.28-point improvement in mental health on the MHI-5 scale (95% CI: 1.17, 1.40; P < 0.001). When the fixed effects was combined with the instrumental variable analysis, a 1-point increase psychosocial job quality is related to 1.62-point improvement on the MHI-5 scale (95% CI: −0.24, 3.48; P = 0.088). Conclusions Our quasi-experimental results provide evidence to confirm job stressors as risk factors for mental ill health using methods that improve causal inference.",
keywords = "fixed effect regression, instrumental variable analysis, MENTAL HEALTH, work",
author = "Allison Milner and Zoe Aitken and Kavanagh, {Anne M} and LaMontagne, {Anthony D.} and Frank Pega and Dennis Petrie",
year = "2017",
month = "6",
doi = "10.1093/pubmed/fdx070",
journal = "Journal of Public Health",
issn = "1741-3842",
publisher = "Oxford University Press",

}

TY - JOUR

T1 - Combining fixed effects and instrumental variable approaches for estimating the effect of psychosocial job quality on mental health

T2 - Journal of Public Health

AU - Milner,Allison

AU - Aitken,Zoe

AU - Kavanagh,Anne M

AU - LaMontagne,Anthony D.

AU - Pega,Frank

AU - Petrie,Dennis

PY - 2017/6/23

Y1 - 2017/6/23

N2 - Background Previous studies suggest that poor psychosocial job quality is a risk factor for mental health problems, but they use conventional regression analytic methods that cannot rule out reverse causation, unmeasured time-invariant confounding and reporting bias. Methods This study combines two quasi-experimental approaches to improve causal inference by better accounting for these biases: (i) linear fixed effects regression analysis and (ii) linear instrumental variable analysis. We extract 13 annual waves of national cohort data including 13 260 working-age (18–64 years) employees. The exposure variable is self-reported level of psychosocial job quality. The instruments used are two common workplace entitlements. The outcome variable is the Mental Health Inventory (MHI-5). We adjust for measured time-varying confounders. Results In the fixed effects regression analysis adjusted for time-varying confounders, a 1-point increase in psychosocial job quality is associated with a 1.28-point improvement in mental health on the MHI-5 scale (95% CI: 1.17, 1.40; P < 0.001). When the fixed effects was combined with the instrumental variable analysis, a 1-point increase psychosocial job quality is related to 1.62-point improvement on the MHI-5 scale (95% CI: −0.24, 3.48; P = 0.088). Conclusions Our quasi-experimental results provide evidence to confirm job stressors as risk factors for mental ill health using methods that improve causal inference.

AB - Background Previous studies suggest that poor psychosocial job quality is a risk factor for mental health problems, but they use conventional regression analytic methods that cannot rule out reverse causation, unmeasured time-invariant confounding and reporting bias. Methods This study combines two quasi-experimental approaches to improve causal inference by better accounting for these biases: (i) linear fixed effects regression analysis and (ii) linear instrumental variable analysis. We extract 13 annual waves of national cohort data including 13 260 working-age (18–64 years) employees. The exposure variable is self-reported level of psychosocial job quality. The instruments used are two common workplace entitlements. The outcome variable is the Mental Health Inventory (MHI-5). We adjust for measured time-varying confounders. Results In the fixed effects regression analysis adjusted for time-varying confounders, a 1-point increase in psychosocial job quality is associated with a 1.28-point improvement in mental health on the MHI-5 scale (95% CI: 1.17, 1.40; P < 0.001). When the fixed effects was combined with the instrumental variable analysis, a 1-point increase psychosocial job quality is related to 1.62-point improvement on the MHI-5 scale (95% CI: −0.24, 3.48; P = 0.088). Conclusions Our quasi-experimental results provide evidence to confirm job stressors as risk factors for mental ill health using methods that improve causal inference.

KW - fixed effect regression

KW - instrumental variable analysis

KW - MENTAL HEALTH

KW - work

U2 - 10.1093/pubmed/fdx070

DO - 10.1093/pubmed/fdx070

M3 - Article

JO - Journal of Public Health

JF - Journal of Public Health

SN - 1741-3842

ER -