Rényi statistics for testing composite hypotheses in general exponential models.
No Thumbnail Available
Full text at PDC
Publication date
2004
Authors
Advisors (or tutors)
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Taylor & Francis
Citation
Bhattacharyya, A. (1946). On some analogues to the amount of information and their uses in statistical estimation. Sankhya, 8, 1–14.
Küchler, U. and Sørensen, M. (1994). Exponential families of stochastic processes and Lévy processes. Journal of Statistical Planning and Inference, 39, 211–237.
Küchler, U. and Sørensen, M. (1997). Exponential Families of Stochastic Processes. Springer-Verlag, Berlin.
Kullback, S. (1959). Information Theory and Statistics. J. Wiley, New York.
Liese, F. and Vajda, I. (1987). Convex Statistical Distances. Teubner, Leipzig.
Morales, D., Prado, L., and Vajda, I. (1997). Some new statistics for testing hypotheses in parametric models. Journal of Multivariate Analysis, 62, 137–168.
Morales, D., Pardo, L. and Vajda, I. (2000). Rényi statistics in directed families of exponential experiments. Statistics, 34, 151–174.
Morales, D., Prado, L., Pardo, M. C. and Vajda, I. (2000). Extension of the Wald statistic to models with dependent observations. Metrika, 52, 97–113.
Pardo, L., Pardo, M. C. and Zografos, K. (1999). Homogeneity for multinomial populations based on φ -divergences. Journal of the Japan Statistical Society, 29, 213–228.
Serfling, R. J. (1980). Approximation Theorems of Mathematical Statistics. Wiley, New York.
Vladimirov, V. S. (1965). Methods of the Theory of Functions of Many Complex Variables. The M.I.T. Press, Massachusetts.
Abstract
We introduce a family of Renyi statistics of orders r is an element of R for testing composite hypotheses in general exponential models, as alternatives to the previously considered generalized likelihood ratio (GLR) statistic and generalized Wald statistic. If appropriately normalized exponential models converge in a specific sense when the sample size (observation window) tends to infinity, and if the hypothesis is regular, then these statistics are shown to be chi(2)-distributed under the hypothesis. The corresponding Renyi tests are shown to be consistent. The exact sizes and powers of asymptotically alpha-size Renyi, GLR and generalized Wald tests are evaluated for a concrete hypothesis about a bivariate Levy process and moderate observation windows. In this concrete situation the exact sizes of the Renyi test of the order r = 2 practically coincide with those of the GLR and generalized Wald tests but the exact powers of the Renyi test are on average somewhat better.