On the Theory of Residual Analyses and Abnormal Performance Metrics

In spite of the proliferation of alternative API metrics, little interpretation and comparison of them has been conducted. Their relationship with the capital asset pricing model has remained obscure. This paper attempts to clarify these and other issues. The major conclusion is that API (or residual) analysis is not satisfactory for testing market efficiency and, therefore, it seems premature to conclude that available evidence is consistent with efficiency.