2013-01: In Search of a Statistically Valid Volatility Risk Factor

Theory predicts that aggregate volatility ought to be a priced risk factor. In an influential study with more than 1000 citations on Google Scholar, Ang, Hodrick, Xing, and Zhang (2006) propose an ex post factor, F V IX, intended as a proxy for aggregate volatility risk. Their test validating F V IX relies on an OLS regression of portfolio excess returns on F V IX and other independent variables over the data period February 1986–January 2001. October 1987 is an outlier, in which F V IX exhibits a 26-sigma deviation. The inclusion of this outlier results in a reduction of the regression standard error by more than a factor of two, creating the appearance of statistical significance when none is present. We explain how standard statistics can be used to assess the suitability of a dataset for OLS regression.