Do dominant or less dominant firms innovate more? Theoretically it has been shown that within an asymmetric mixed strategy game of a patent race, the less dominant firm invests more than the dominant firm. But the empirical data on patent races is divided. In this paper, we argue that the decisions that concern strategic choice in innovation may be influenced by expected relative returns. Our approach, which we call the returns-based beliefs approach, is based upon subjective probabilities. It combines a decision analytic solution concept and Luce’s (1959) probabilistic choice model. In particular, we show how the use of the returns-based beliefs approach provides support for the thesis that dominant firms invest more in R&D within an asymmetric mixed strategy game. Consequently, we argue that the returns-based beliefs approach is more in line with recent empirical studies of innovation. We also provide empirical evidence using UK R&D data across a range of industries from 2001-2006 that shows that firms’ spending on R&D is related more to their own profitability than that of their competitors, which is consistent with the returns-based beliefs approach. We discuss the managerial implications of our theoretical approach and the empirical findings.