A0432
Title: Hansen-Jagannathan distance with many assets
Authors: Marine Carrasco - Université de Montréal (Canada) [presenting]
Cheikh Nokho - University of Montreal (Canada)
Abstract: The evaluation of asset pricing models is examined with many test assets. Two interpretable regularization schemes are implemented to extend the Hansen-Jagannathan distance in a framework of a data-rich environment. These regularizations are a relaxation of the fundamental equation of asset pricing and therefore take into account the global misspecified nature of models in finance. It is used to provide asymptotic distribution of stochastic discount factor parameters and implement comparison tests of asset pricing models. The asymptotic properties of the tests of equality of SDF and test of equality of HJ distances are also derived for competing asset pricing models when both the number of assets N and the time dimension T go to infinity. Simulations show that regularization permits to obtain better size and power than unregularized estimators. Next, the comparison tests are applied to 7 popular models.
