In this article, we apply recent advances in quasi-experimental estimation methods to analyze the effectiveness of Germany’s large-scale regional policy instrument, the joint Federal Government/State Programme "Gemeinschaftsaufgabe Verbesserung der regionalen Wirtschaftsstruktur" (GRW), which is a means to foster labor-productivity growth in lagging regions. In particular, adopting binary and generalized propensity-score matching methods, our results indicate that the GRW can be generally considered effective. However, we find evidence for a nonlinear relationship between GRW funding and regional growth associated with a maximum subsidy level beyond which financial support does not generate further labor-productivity growth. In other words, there is a "purchase limit" on regional growth. Although the matching approach is very appealing due to its methodological rigor and didactical clarity, throughout the empirical application, we faced difficulties in balancing the set of covariates among treated and comparison regions, given that two sets of the regions differ strongly with respect to their underlying structural characteristics. Such imperfect balancing may limit the practical applicability of matching techniques in regional data settings. Overall, however, the matching approach can still be considered of great value for regional policy analysis and should be the subject of future research efforts in the field of empirical regional science.