Showing papers by "Rahul Mukerjee published in 1990"
TL;DR: In this paper, the authors investigated the robustness of group divisible (GD) designs when one block is lost, in terms of efficiency of the residual design, and showed that GD designs are fairly robust.
Abstract: Robustness of group divisible (GD) designs is investigated, when one block is lost, in terms of efficiency of the residual design. The exact evaluation of the efficiency can be made for singular GD and semi-regular GD designs as ell as regular GD designs with λ1 = 0. In a regular GD design with λ1 > 0, the efficiency may depend upon the lost block and sharp upper and lower bounds on the efficiency are presented. The investigation shows that GD designs are fairly robust in terms of efficiency. As a special case, we can also show the robustness of balanced incomplete block design when one block is lost.
18 citations
TL;DR: In this article, it is shown that in a multiparameter setting, under contiguous alternatives, unlike in the one-parameter case, identity of power up to the first order may not imply that up to second order.
17 citations
TL;DR: In this article, different superpopulation models for a finite population with linear trend were proposed and optimal sampling strategies for estimating the finite population mean within some classes of unbiased strategies were proposed.
Abstract: SUMMARY Postulating different superpopulation models for a finite population with linear trend, we suggest optimal sampling strategies for estimating the finite population mean within some classes of unbiased strategies.
16 citations
TL;DR: In a general multiparameter setup, this article proved an optimality property of Rao's test, in terms of maximization of the average third-order power under contiguous alternatives, within a very wide class of tests that includes the likelihood ratio and Wald's tests.
16 citations
TL;DR: In this paper, the A-optimal rotatable design measures for fourth-order polynomial regression on hyperspheres were derived for the triangular association scheme and the application of the association algebra of triangular association schemes is helpful in the derivation of the objective function.
11 citations
TL;DR: In this paper, the theory of unimodular matrices has been applied to derive D-optimal main effect plans for 1 ×s 2 factorials and for 1 +s 2 runs.
Abstract: The theory of unimodular matrices has been applied to deriveD-optimal main effect plans fors
1 ×s
2 factorials ins
1 +s
2 runs. Plans with highA-efficiency have also been given.
8 citations
TL;DR: In this article, it was shown that with a suitably chosen random confidence coefficient, depending on second stage variation, one can be closer in the mean square sense to the indicator specifying whether a normal mean lies in a bounded length confidence interval, than the constant confidence coefficient 1 −α.
Abstract: ABSTRACT: With reference to Stein's two‐stage sampling, it is shown that with a suitably chosen random confidence coefficient, depending on second stage variation, one can be closer in the mean square sense to the indicator specifying whether a normal mean lies in a bounded length confidence interval, than the constant confidence coefficient 1‐α. The efficiency of the constant confidence coefficient 1‐α. as a predictor of this indicator, has also been investigated.
6 citations
TL;DR: In this article, an approximate theory for the optimality of balanced designs under minimum norm quadratic unbiased estimation of variance components in one-way classified data was developed, where the objective function is to minimize the variance of the balanced design.
Abstract: This paper develops an approximate theory for the optimality of balanced designs under minimum norm quadratic unbiased estimation of variance components in one-way classified data.
4 citations
TL;DR: In this article, the optimal exponential order quantity, which maximizes the minimum profit obtainable in the NBUE class of supply distributions, is a function of the demand distribution function, and it is shown that an estimator of the maximin order quantity which is already known to converge almost surely to its true value, converges also in distribution to an appropriate normal law with increasing sample size.
Abstract: A one-period inventory situation where the supply is an NBUE random variable with mean proportional to the quantity ordered has been considered. The optimal exponential order quantity, which maximizes the minimum profit obtainable in the NBUE class of supply distributions, is a function of the demand distribution function. Here we show that an estimator of the maximin order quantity, which is already known to converge almost surely to its true value, converges also in distribution to an appropriate normal law with increasing sample size.
2 citations
TL;DR: In this article, the authors considered a situation where the manufacturer of a two component product receives supplies of the two eomponents presumably from two different sources each supplying components of one variety.
Abstract: :This paper considers a situation where the manufacturer of a two‐component product receives supplies of the two eomponents presumably from two different sources each supplying components of one variety. Under NBUE assumption on both the supply random variables, a strategy which maximizes the minimum expected profit in a one‐period inventory model, with uncertainty in demand, has been explored. An estimator for this maximin order quantity whenever the demand distribution is unknown has been proposed and almost sure convergence· of this estimator to its true value has been established. Further asymptotic results helpful in testing or interval estimation problems concerning the maximin order quantity have also been derived.AMS 1980 Subject Classification: 90B05, 60F05.