Multilevel heterogeneity of R&D cooperation and innovation determinants

Assessing the impact of public support to innovation on R&D collaboration may require a more complex multilevel design, that describes the likely correlation present among firms characteristics within a particular sector. Using data from the 2006 edition of the Community Innovation Survey (CIS) for the Netherlands, we propose a methodology to study the effect of firm-level characteristics on the propensity to undertake a research collaborative agreement. In particular, we show that controlling for a richer variance structure yields a different picture with respect to simpler regression frameworks adopted in the literature of R&D cooperation determinants. Moreover, such a hierarchical framework can be generalized allowing for clustering at higher levels, such as sectors or geographical areas. Besides the link between public funding and R&D collaboration, our results confirm the findings of the literature: technological spillovers, risk and cost sharing rationales, firm's size, and type of innovative activity are related to the decision of engaging in different sorts of research alliances.