“Testing Factor-Model Explanations of Market Anomalies” by Sheridan Titman
University of Texas at Austin
A set of recent papers attempts to explain the size and book-to-market anomalies with either: (1) conditional CAPM or conditional consumption-CAPM models with economically motivated conditioning variables, or (2) factor models based on economically motivated factors. The tests of these models use similar methodologies and similar test assets, and each test fails to reject the proposed model. This is surprising, as the correlation between the proposed factors is very small. We argue that many or all of these tests may fail to reject as a result of low statistical power. We propose an alternative test methodology which provides higher power against reasonable alternative hypotheses, and show that the new test methodology results in the rejection of several of the proposed factor models at high levels of statistical significance.