A tutorial on a marginal structural modeling approach to mediation analysis in occupational health research:...

Life expectancy inequities between more- and less-educated groups have grown by 1 to 2 years over the last several decades in the United States. Simultaneously, employment conditions for many workers have deteriorated. Researchers hypothesize that these adverse conditions mediate educational inequities in mortality. However, methodological barriers have impeded research on the role of employment conditions and other hazards as mediating factors in health inequities. Indeed, traditional mediation analysis methods are often biased in occupational health settings, including in those with exposure-mediator interactions and mediator-outcome confounders that are caused by exposure. In this paper, we outline-and provide code for-a marginal structural modeling (MSM) approach for estimating total effects and controlled direct effects originally proposed elsewhere, which can be applied to common mediation analysis settings in occupational health research. As an example, we apply our approach to assess the extent to which disparities in employment quality (EQ)-a multidimensional construct characterizing the terms and conditions of the worker-employer relationship-explained educational inequities in mortality in a 1999-2015 US Panel Study of Income Dynamics sample of workers with mortality follow-up through 2017. Under certain strong assumptions described in the text, our estimates suggest that over 70% of the educational inequity in mortality would have been eliminated if EQ had been at the 80^th percentile (100^th  = best) across exposure groups.