On distinguishing the direct causal effect of an intervention from its efficiency-enhancing effects

This paper proposes an innovative methodology for handling endogeneity issues in the evaluation of policy performance. By estimating a regression discontinuity design with a four-component stochastic frontier panel data model, we estimate the causal impact of a policy intervention on the outcome variable, whenever the treatment status depends on an exogenous threshold. We distinguish between (i) the direct effect of the intervention, (ii) the efficiency-enhancing effect, or (iii) their combination. Moreover, we distinguish between persistent (time-invariant) and transient (time-varying) inefficiency components while accounting for unobserved heterogeneity, which is important for policy implications. We showcase the practical usefulness of the proposed approach by estimating the effect of providing additional resources on schools that exceed an exogenously set share of disadvantaged students in secondary schools in Flanders, Belgium. We also demonstrate the trade-off between balance of the covariates in the treated and control group and statistical power. Thus, despite insignificant effects in a balanced but smaller sample close to the discontinuity, the results become significant in the unbalanced sample with more statistical power. In both samples, we observe that the policy had an effect on the outcome mostly through the efficiency-enhancing channel. To this extent, we show that the model specification including both direct and indirect effects outperforms the other two specifications and it offers a more exhaustive perspective from a policy view point.