Mediation analysis for associations of categorical variables: The role of education in social class mobility in Britain

We analyse levels and trends of intergenerational social class mobility among three postwar birth cohorts in Britain examine how much the observed or immobility them could be accounted for by existing differences educational attainment between people from different backgrounds. propose this purpose a method which quantifies associations categorical variables when we compare groups differ only distribution mediating variable, such as education. This is analogous to estimation indirect effects causal mediation analysis but here developed define estimate population variables. estimators these depend on fitted values models mediator outcome variables, variance them. The shows that part education play no means so dominant has been supposed that, while it varies with gender particular transitions, tendency change over time.