Answers are grounded in this paper and cite their sources.
There are given a populations Π₁, ⋯, Πₐ, of which we wish to select a subset. The quality of the ith population is characterized by a real-valued parameter θᵢ, and a population is said to be {align*}{1} positive (or good) if θ_i & θ_0 + Δ, \\ {2} negative {(or} bad) if θ_i & θ_0,{align*} where Δ is a given positive constant and θ₀ is either a given number or a parameter that may be estimated. A number of optimum properties of selection procedures are defined (Section 3) and it is shown that for some of these, the optimum procedure selects Πᵢ when {equation*}{3}T_i C_i,{equation*} where Tᵢ is a suitable statistic, the distribution of which depends only on θᵢ, and where C is a suitable constant. (Sections 4 and 6.) Applications are given to distributions with monotone likelihood ratio in the case that θ₀ is known (Sections 5 and 6), and to normal distributions when instead observations on θ₀ are included in the experiment (Sections 10 and 11).
No takes yet. Share an insight, caveat, or question.
E. L. Lehmann (1961) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: