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.