Abstract
The principal result of APT is the arbitrage pricing condition that expected returns can be approximated by a linear combination of risk with strongly bounded pricing errors. Existing tests of APT either assume the pricing error to be zero or of order one in probability. Neither assumption is consistent with the theory of APT. In this paper, we characterize the pricing errors in terms of orders of probability. Errors consistent with APT are shown to be of order 1/SQRT(N) in probability where N is the number of assets. A test for APT is then a test of the order of the pricing error. We construct such a test based on tests for heteroscedasticity across sequences of assets. In a simulation study for both known and unknown factor structures, we show that this test performs better than existing tests for detecting violations of arbitrage pricing. In a study of US equities from 1978-2002, we find that the strongest evidence for arbitrage pricing is in single-factor models.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
