R&D Spillover Effects on Firm Innovation – Estimating the Spatial Matrix from Panel Data

Firms' research and development (R&D) efforts are known to have spillover effects on other firms' outcomes, e.g., innovation. Quantifying R&D spillover effects requires a spatial matrix that characterises the interaction structure between firms. Estimates can be biased if the spatial matrix is misspecified. This paper proposes a parsimonious approach to estimating the spatial matrix and parameters from panel data, when the spatial matrix is partly or fully unknown. The approach is robust to misspecification of the spatial matrix, and it is applicable to single index models. It allows asymmetry and time-variation in the spatial matrix. The paper establishes consistency and asymptotic normality of the MLE under conditional independence and conditional strong-mixing assumptions on the outcome variable. On firm innovation, I find positive spillover and private effects of R&D. I provide evidence of time-variation and asymmetry in the interaction structure between firms and find that geographic proximity and product market proximity are relevant. Moreover, connectivity between firms is not limited to often-assumed notions of proximity; it is also linked to past R&D and patenting behaviour of firms