Large differences in mortality rates across those with different levels of education are a well-established fact. This association between mortality and education may partly be explained by confounding factors, including cognitive ability. Cognitive ability may in turn be affected by education so that it becomes a mediating factor in the causal chain. This paper develops an inverse probability weighted (IPW) estimator to analyse this mediating effect in the context of survival models.

Using administrative data on men born in 1944-1947 who were examined for military service in the Netherlands between 1961-1965 linked to national death records, we decompose the impact of education on mortality into a direct educational effect and an indirect effect through intelligence. For these men we distinguish four education levels and make pairwise comparisons.