This article is cited in 4 papers

Aysmptotically optimal tests of testing hypotheses for an interdependent sample

A. F. Kušnir, A. I. Pinskiĭ

Moscow

Abstract: The paper deals with testing the hypothesis that the sample has been taken from a $k$-dependent stationary Markov chain against the alternative that the transition function depends on a “signal” as a parameter.
The problem is treated “asymptotically”, i.e. as the sample size tends to infinity while the signal “amplitude” decreases. The methods used are based on the study of asymtotical behaviour of the likelihood ratio. Asymptotically optimal (and in some cases rank-order asymptotically optimal) tests are effectively constructed, and their properties are studied.

Received: 22.10.1969

 English version: Theory of Probability and its Applications, 1971, 16:2, 281–292

Bibliographic databases:

• 
•