Skip to main content
Article
A Monte Carlo analysis of two spectral tests of the martingale hypothesis
Journal of the Italian Statistical Society (1996)
  • Claudio Lupi, University of Molise
Abstract

The size, power, and robustness properties ofthe Kolmogorov-Smimov and Cramér-von Mises spectral tests of the martingale (difference) hypothesis are investigated by Monte Carlo methods. The results highlight a marked superiority of the Cramé-von Mises with respect to the Kolmogorov-Smimov test. The paper also shows that the Cramér-von Mises test is simple to compute, more generai and more powerful than other conventionally used tests.

Publication Date
1996
Citation Information
Claudio Lupi. "A Monte Carlo analysis of two spectral tests of the martingale hypothesis" Journal of the Italian Statistical Society Vol. 5 Iss. 3 (1996)
Available at: http://works.bepress.com/claudio_lupi/23/