Replication data for "Direct and indirect effects of continuous treatments based on generalized propensity score weighting"

The data set comes from the public use data of the Job Corps experimental study, a U.S. educational intervention for disadvantaged youth, to demonstrate the application of causal mediation analysis with a continuous treatment variable. The application (see R code) disentangles the effect of time spent in academic or vocational training on crime into an indirect effect operating through the mediator employment and a direct (remainder) effect covering any other causal mechanisms.