Optimal allocation of observations in one-way random normal model
In the note under review complements in terms of \textit{L. Le Cam}'s deficiency relation [Ann. Math. Stat. 35, 1419--1455 (1964; Zbl 0129.11202)] are given to the results of \textit{M. H. De Groot} [Ann. Inst. Stat. Math. 18, 13--28 (1966; Zbl 0149.15502)] on allocations (of observations) in a one-way normal model when both variance components are known and the number of subclasses is not fixed. The theorems presented concern three cases: that the number of subclasses is fixed (the most uniform allocation is optimal), that one of the variance components is unknown (an optimal allocation exists), and that both variance components are unknown (no two essentially different allocations are comparable). The approach to the problems solved in this paper naturally relies on the contribution of \textit{O. H. Hansen} and \textit{E. N. Torgersen} [Ann. Stat. 2, 367--373 (1974; Zbl 0289.62011)] on the comparison of linear normal experiments.
- Optimal Allocation of Observations for Inference on k Ordered Normal Population Means
- scientific article; zbMATH DE number 4043089
- scientific article; zbMATH DE number 3892368
- Understanding sufficiency in one-way random effects model
- Optimal Bayesian design of experiments for the one-way random effects model
- On the optimum number of levels in the one-way model with random effects
- Understanding sufficiency in one-way random effects model
- Optimal Allocation of Observations for Inference on k Ordered Normal Population Means
- Stochastic ordering and Schur-convex functions in comparison of linear experiments
- Optimal allocation of units in experimental designs with hierarchical and cross classification
This page was built for publication: Optimal allocation of observations in one-way random normal model
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1169768)