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

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: .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.