Empirical Tests of Asset Pricing Models with Individual Assets : Resolving the Errors-in-Variables Bias in Risk Premium Estimation

To attenuate an inherent errors-in-variables bias, portfolios are widely employed to test asset pricing models; but portfolios might mask relevant risk- or return-related features of individual assets. We propose an instrumental variables approach that allows the use of individual stocks as test assets, yet delivers consistent estimates of ex-post risk premiums. This estimator also yields well-specified tests in small samples. The market risk premium under the CAPM and the liquidity-adjusted CAPM, premiums on risk factors under the Fama-French three- and five-factors models and the Hou, Xue, and Zhang (2015) four-factor model are all insignificant after controlling for asset characteristics