Abstract
The asymptotic behavior of multiple decision procedures is studied when the underlying distributions belong to an exponential family. An adaptive procedure must be asymptotically optimal for each value of the unknown nuisance parameter, on which it does not depend. A necessary and sufficient condition for the existence of such a procedure is discussed. The regions of the parameter space, where the traditional overall maximum likelihood rule is adaptive, are described. The examples of a normal family and a family of gamma-distributions are considered in detail.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bickel, P. A., Klaassen, C. A. J., Ritov, J. and Wellner, J. A. (1993). Efficient and Adaptive Estimation for Semiparametric Models, Baltimore: Johns Hopkins University Press.
Chernoff, H. (1956). Large-sample theory: Parametric case, Annals of Mathematical Statistics, 27, 1–22.
Krafft, O. and Puri, M. L. (1974). The asymptotic behavior of the minimax risk for multiple decision problems, Sankhya A, 36, 1–12.
Renyi, A. (1970). On some problems of statistics from the point of view of information theory, In Proceedings of the Colloquium on Information Theory-2, pp. 343–357, Budapest, Hungary: Bolyai Mathematical Society.
Rukhin, A. L. (1982). Adaptive procedures for a finite number of probability distributions families, In Proceedings of Third Purdue Symposium on Decision Theory-1 (Eds. S. S. Gupta and J. O. Berger), pp. 269–286, New York: Academic Press.
Rukhin, A. L. (1984). Adaptive classification procedures, Journal of the American Statistical Association, 79, 415–422.
Stein, C. (1957). Efficient nonparametric testing and estimation, In Proceedings of Third Berkeley Symposium on Mathematical Statistics and Probability-1, pp. 187–196, Berkeley: University of California Press.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1997 Birkhäuser Boston
About this chapter
Cite this chapter
Rukhin, A.L. (1997). Adaptive Multiple Decision Procedures for Exponential Families. In: Panchapakesan, S., Balakrishnan, N. (eds) Advances in Statistical Decision Theory and Applications. Statistics for Industry and Technology. Birkhäuser Boston. https://doi.org/10.1007/978-1-4612-2308-5_7
Download citation
DOI: https://doi.org/10.1007/978-1-4612-2308-5_7
Publisher Name: Birkhäuser Boston
Print ISBN: 978-1-4612-7495-7
Online ISBN: 978-1-4612-2308-5
eBook Packages: Springer Book Archive