Examination of the behavior of R&D returns using a power law

Science and Public Policy. 2013. Vol. 40. No. 2. P. 219–228.

Casault S., Groen A. J., Linton J. D.

This paper provides an improved model, based on historical data, that describes the returns on assets that result from R&D efforts to assist managers of public and private R&D activities. Such a model may lead to better decision support tools to monetize the value that may be extracted from R&D, which is otherwise often undervalued. Real option pricing models are used to gauge appropriate funding levels for assets such as R&D projects that contain large time-dependent uncertainties. However, this study finds that assuming the Gaussian distribution describes fluctuations in value is not appropriate for assets whose value is derived from R&D activities. This conclusion is based on a study of 43 military R&D projects and 100 technology-intensive small firms. A power law, such as the Cauchy distribution, is shown to be more accurate in describing fluctuations in returns from R&D investments.

Keywords: innovation, Cost-benefit analysis, decision support systems, power law distribution, Black-Scholes, Cauchy distribution, real option, thick tail, accuracy assessment, industrial technology, uncertainty analysis