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: Contribution to journalArticleResearchpeer-review

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
Pages426-434
Number of pages9
JournalJournal of Public Health
Volume40
Issue number2
DOIs
StatePublished - May 2018

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 = "2018",
month = "5",
doi = "10.1093/pubmed/fdx070",
language = "English",
volume = "40",
pages = "426--434",
journal = "Journal of Public Health",
issn = "1741-3842",
publisher = "Oxford University Press",
number = "2",

}

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

In: Journal of Public Health, Vol. 40, No. 2, 05.2018, p. 426-434.

Research output: Contribution to journalArticleResearchpeer-review

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 - 2018/5

Y1 - 2018/5

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

VL - 40

SP - 426

EP - 434

JO - Journal of Public Health

JF - Journal of Public Health

SN - 1741-3842

IS - 2

ER -