Absorptive capacity and R&D tax policy: Are in-house and external contract R&D substitutes or complements?

Firms fund research and development (R&D) to generate commercializable innovations and to increase their ability to understand and absorb knowledge from elsewhere. This dual role and opposed incentive structure of internal R&D create a significant question for both theory and R&D policy: Is internal R&D a complement or substitute for external R&D? We develop a model and novel technique for empirically estimating R&D substitution elasticities. We focus on bio-pharmaceutical and software industries in California and Massachusetts, where tax credit rates changed differently over time for the two types of R&D, creating a natural experiment. The effective tax prices for the two R&D types differ from type to type, firm to firm, state to state, and year to year. This allows us to examine changes in the composition of firms' R&D budgets between in-house R&D and external basic research when the relative tax prices of each category of research change. We find evidence of a substitute relationship both for a sample comprising exclusively small firms as well as for a more general distribution of firm sizes.