The Impact of Capital Subsidies: New Estimations under Continuous Treatment

Most of the relevant literature on the evaluation of the impact of public subsidies to private firms deals with the estimation of causal effects of a binary treatment. However, several policies allow for different levels of subsidies, depending on the investment project, the firm dimension, the region and also on the firms’ choice. The aim of the paper is to evaluate the causal effect of a policy intervention in the case of a continuous treatment, exploring the impact of differences in treatment level on policy outcome. As an empirical application, we estimated the impact of subsidies allocated by L. 488/1992, the main regional policy in Italy, in the southern regions of the country in the period 1996-2000. We compare two estimation methods: a parametric method, based on a more traditional DID estimator adapted to the continuous treatment case, and a non parametric estimator, based on a novel two-step matching method developed in our recent work (Adorno, Bernini and Pellegrini, 2007a). On average, our results support the conclusions derived from methods based on the binary treatment: subsidies have a positive and often statistically significant effect on employment, fixed assets and turnover. However, the strong heterogeneity of the treatment outcome with respect to different levels of treatment is highlighted. We find that higher the level of incentive, higher the policy effect until a certain point, from which the marginal impact decreases. The results are robust to changes in the estimation method.