Abstract
This paper applies an asymptotic principal components technique, developed by Connor and Korajczyk (1988), to test an equilibrium version of the Arbitrage Pricing Theory (APT), which permits time varying risk premia, using Australian equity data. Cross-equation restrictions imposed by the APT on a multivariate regression of excess returns on derived factors are tested. Both one-step and iterative versions of the technique are used and results are compared to the capital asset pricing model (CAPM). While the APT appears to perfor M better than the CAPM, neither model can adequately explain monthly seasonal mispricing in Australian equities.
Get full access to this article
View all access options for this article.
