On the basis of the residual income model, we propose a statistical model for inferring implied cost of equity (COE) from cross-sectional data on stock prices and firms' attributes. The model is estimated using a quasimaximum likelihood approach to simultaneously identify the COE, expected earnings growth rates, and expected excess earnings durations of individual Japanese firms listed on the First Section of the Tokyo Stock Exchange (excluding the financial industry sector). The estimation results show that the individual firms' attributes, such as industry sector, cash-flow/price ratio, and dividend/price ratio, are key determinants of the COE. Besides, we find that the distribution of individual firms' COE has changed over time, which suggests that it is crucial to take account of market conditions and financial situations of the firms in the estimation. Moreover, our estimates of the firms' COE have a positive relation with expected returns on their stocks, and the relation is stronger than those obtained with existing models.
Keywords: Implied cost of equity; Residual income model; Quasimaximum likelihood approach
Views expressed in the paper are those of the authors and do not necessarily reflect those of the Bank of Japan or Institute for Monetary and Economic Studies.