Kourouklis, Stavros Bahadur optimality of sequential experiments for exponential families. (English) Zbl 0561.62071 Ann. Stat. 12, 1522-1527 (1984). The concept of Bahadur efficiency was extended to sequential analysis by R. M. Berk and L. D. Brown [ibid. 6, 567-581 (1978; Zbl 0403.62055)] who showed optimality of certain modifications of the likelihood ratio statistic for one-sided hypotheses about the mean of a normal distribution. In this paper, the result of Berk and Brown is generalized to general hypotheses for exponential families. Reviewer: A.Irle MSC: 62L10 Sequential statistical analysis 62F05 Asymptotic properties of parametric tests 60F10 Large deviations Keywords:asymptotic optimality; stopping times; Bahadur efficiency; likelihood ratio statistic; general hypotheses for exponential families Citations:Zbl 0403.62055 × Cite Format Result Cite Review PDF Full Text: DOI