Summary
This paper is concerned with the reduction to a complete class of decision rule in case where actions, observations and states are finite in number. Discussions are made, first, from the viewpoint of the distribution of random observation and, secondly, from the viewpoint of loss function. With respect to loss function, “regret-relief ratio” criterion and “incremental loss-gain ratio” criterion are introduced and these usefulness are shown in 2-state of nature case.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Karlin, S. and Rubin, H. (1956). The theory of decision procedures for distributions with monotone likelihood ratio,Ann. Math. Statist., 27, 272–299.
Chernoff, H. and Moses, L. E. (1959).Elementary Decision Theory, John Wiley & Sons, New York.
Ferguson, T.S. (1967).Mathematical Statistics: A Decision Theoretic Approach, Academic Press, New York.
Additional information
The Institute of Statistical Mathematics
An erratum to this article is available at http://dx.doi.org/10.1007/BF02504767.
About this article
Cite this article
Murakami, M. On the reduction to a complete class in multiple decision problems. Ann Inst Stat Math 28, 145–165 (1976). https://doi.org/10.1007/BF02504737
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02504737