This paper uses a new data set of 12,000 firms in China to estimate the returns to research and development investment and its spillover effects, and investigates how the returns to research and development depend on firm incentives. For the firms in the sample, the results show that on average firm output increases around 0.4 yuan for each additional 1 yuan spent on research and development in the previous year, and there is high research and development return regardless of whether the analysis deals with the endogeneity of research and development intensity. Interestingly, the marginal return to research and development is significantly higher in firms whose chief executive officers were not appointed by the government and lower when the chief executive officer's pay is directly related to annual performance. The return to research and development is higher in relatively poor regions and for firms with worse access to finance. There are also non-trivial research and development spillover effects.