This paper provides evidence on the effectiveness of R&D incentives to private firms allocated by Region Umbria in the period between 2004 and 2009. The methodological innovation proposed in this paper is a novel spatial Difference-in-Difference estimator. Our approach compares distinct treatment effects on the basis of the localization in the main local market areas of Umbria (Perugia and Terni), controlling for the presence of technological spillovers due to geographical and economic proximity. The results show a positive and statistically significant impact of the subsidies, especially for innovative outputs and for small firms. The impact is higher for the firms located outside the main labour market areas, suggesting the presence of significant local technological spillovers due to the conjunct action of regional policies and geographical concentration. Finally, this paper provides some empirical evidence in favour of the effectiveness of ”place-based” innovation policies which constitutes the ”core" of the recent smart specialization strategy. During the last decades SUTVA has represented the "gold standard" for the identification and evaluation of causal effects. However, the presence of interferences in causal analysis requires a substantial review of the SUTVA hypothesis. This paper proposes a framework for causal inference in presence of spatial interactions within a new spatial hierarchical Differencein-Differences model (SH-DID). The novel approach decomposes the ATE (Average Treatment Effect), allowing the identification of direct (ADTE) and indirect treatment effects. In addition, our approach permits the identification of different indirect causal impact both on treated (AITET) and on controls (AITENT). The performance of the SH-DID are evaluated by a Montecarlo Simulation. The results confirm how omitting the presence of interferences produces biased parameters of direct and indirect effects, even though the estimates of the ATE in the traditional model are correct. Conversely, the SH-DID provides unbiased estimates of both total, direct and indirect effects. In addition, this model is the more efficient compared both to the traditional and a Spatial modified Difference-in-Differences estimator. Rubin Causal Model explicitly rule out the presence of spatial interferences in the definition and estimation of causal impact. In this way, the traditional approach provide unbiased estimates of the average total effect of the treatment (ATE), but it makes impossible the distinction between direct and indirect (spillover) effects. Di Gennaro and Pellegrini (forthcoming) propose an alternative specification of a Difference-in-Difference estimator, which includes the presence of spatial interaction, and define three different causal effect: the direct (ADTE) and the indirect for both the treated and control group (AITET and AITENT respectively). In this paper we follow the intuition behind the novel methodology in order to find empirical evidences of the diffusion of spillover effects due to the policy in the Italian case.