On testing simple hypotheses in finite time with Hellman-Cover automata
- 1 March 1975
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 21 (2) , 157-162
- https://doi.org/10.1109/tit.1975.1055362
Abstract
Asymptotically\varepsilon-optimal automata were developed by Hellman and Cover [4] for testing simple hypotheses concerning the parameter of an independent identically distributed sequence of Bernoulli random variables. These automata permit transitions only between adjacent states and employ artificial randomization only at extreme states. In this paper we study the problem of approximating the optimal Hellman-Cover automaton in fixed-sample-size problems. It is shown that the optimal level of the parameter, which regulates the probability of transitions out of an extreme state, tends to zero at the rate\ln n/nin symmetric testing problems wherenis the sample size. We develop an approximation for the optimal parameter value valid fornsufficiently large.Keywords
This publication has 6 references indexed in Scilit:
- Random Walks and Undirected Graph Connectivity: A SurveyPublished by Springer Nature ,1995
- On tests with finite memory in finite time (Corresp.)IEEE Transactions on Information Theory, 1974
- Hypothesis testing with finite memory in finite time (Corresp.)IEEE Transactions on Information Theory, 1972
- Learning with Finite MemoryThe Annals of Mathematical Statistics, 1970
- 5578The American Mathematical Monthly, 1969
- Perturbation theory for linear operatorsPublished by Springer Nature ,1966