Abstract
| Original language | English |
|---|---|
| Pages (from-to) | 426-434 |
| Number of pages | 9 |
| Journal | Journal of Public Health |
| Volume | 40 |
| Issue number | 2 |
| DOIs | |
| Publication status | Published - May 2018 |
Keywords
- fixed effect regression
- instrumental variable analysis
- MENTAL HEALTH
- work
Cite this
}
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 journal › Article › Research › peer-review
TY - JOUR
T1 - Combining fixed effects and instrumental variable approaches for estimating the effect of psychosocial job quality on mental health
T2 - evidence from 13 waves of a nationally representative cohort study
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 -