Showing papers in "Journal of Statistical Planning and Inference in 1985"

TL;DR: An iterative solution to the problem of maximizing a concave functional defined on the set of all probability measures on a topological space is considered in this paper, where convergence of this procedure and a rapidly converging algorithm are studied.

TL;DR: If the unknown subset is taken from the family of k-element sets with uniform distribution, the minimum of the lengths of the strategies that find the unknown element with small error probability is determined.

TL;DR: In this paper, the robust procedure for testing mean and variance from nonnormal universe is examined from the Bayesian viewpoint, and the posterior distribution of the scale parameter is derived and then approximated by a Laguerre polynomial expansion while the posterior distributions of the location parameter is approximated using a linear combination of t-distributions.

TL;DR: In this article, the authors proposed a framework and the resultant methods for the problem of detecting and characterizing influential subsets of observations when the goal is to estimate parameters using a Bayesian formulation and Kullback-Leibler divergences.

TL;DR: In this article, the concept of univariate mean remaining life (m.r.l.) function is generalized to the multivariate case and four new classes of multivariate survival distribution functions (s.d.f.'s) are introduced.

TL;DR: In this paper, the problem of determining block designs which are optimal under type 1 optimality criteria within various classes of designs having υ treatments arranged in b blocks of size k was investigated.

TL;DR: In this paper, an algebra generated by the projection matrices associated with a row-column design is used to prove an inequality which was used to derive an efficiency bound for rowcolumn designs.

TL;DR: In this article, the search design of Ghosh (1981) was extended to allow the estimation of the general mean and main effects, and the search and estimation of one possibly unknown nonzero effect among the two-and three-factor interactions in 2m factorial experiments.

TL;DR: In this paper, some kernel-type quantile estimators are considered for random right-censorship data, which give smoother estimates than the usual product-limit quantile function.

TL;DR: In this paper, a generalized Hadamard matrix (GH(4q, EA(q)) was constructed for odd prime powers other than 3 or 5, and a 4 × 4 matrix of q × q blocks was constructed.

TL;DR: In this paper, it was shown that the necessary conditions λ≡0 (mod |G|), λ(υ−1)≡ 0 ( mod 2), λυ −1) ≈ 0 (mod 6) for |G | odd and λ υ− 1)≈ 0(mod 24) for the even case for the generalized Bhaskar Rao design GBRD for the elementary abelian group G.

TL;DR: In this paper, the additive 3 factor linear model is used in Latin square design settings and conditions under which a design is A-optimal or E-optimality are derived and examples given of when these conditions are satisfied.

TL;DR: In this paper, a new estimator of population total for the characteristics that are poorly correlated with the selection probabilities has been developed for the PPSWR sampling scheme, and the relative efficiency of the proposed estimator has been studied under a superpopulation model.

TL;DR: In this paper, a non-asymptotic approach based on the chi-square statistic is described for analyses of r by c contingency tables, which provides improved analyses for cases where the standard asymptotic method is questionable, e.g., with small expected cell frequencies due to severely unbalanced and/or very small marginal frequency totals.

TL;DR: In this paper, the authors established asymptotic normality of U -statistics based on the trimmed sample X n,[ αn ]+1 ≤ ⋯ ≤ X n, n − [ βn ] where 0 1 2.

TL;DR: In this article, an exact formula for the mean squared error of the inverse estimator, involving expectations of functions of a Poisson random variable, is derived, and the formula may be expressed in closed form if the number of observations in the calibration experiment is odd; for an even number of observed, the numerical evaluation of a simple integral or the use of a standard table of the confluent hypergeometric function is required.

TL;DR: In this article, it was shown that the order statistics of general distributions have a certain Markov property for general distributions and that order statistics have monotone conditional regression dependence, which is well known in the case of continuous distributions.

TL;DR: In this paper, two new selection procedures, called nonrandomized and randomized Bayes -P ∗ procdures are defined for selecting a small nonempty subset of k populations which contains the best population.

TL;DR: In this article, three new ratio-cum-product estimators are proposed and the relative efficiencies of all these estimators were studied comparatively, through an empirical study, for the case of a fairly large sample from a large bivariate population.

TL;DR: In this paper, the existence of unbiased definite quadratic estimators is studied in linear models with two variance components and necessary and sufficient conditions for their existence are given. And an unbalanced one-way random model is studied for demonstration.

TL;DR: In this paper, a search design for the 2m type such that at most knonnegative effects can be searched among (l+1)-factor interactions and estimated along with the effects up to l- factor interactions, provided (l + 1)-factor and higher order interactions are negligible except for the k effects.

TL;DR: In this paper, the packing problem of factor screening for searching two and three effective factors using the search linear model is introduced and a complete solution of the problem in one case and partial solutions for the other cases are presented.

TL;DR: In this paper, the problem of minimum variance unbiased estimation for families of distributions involving two truncation parameters is treated, and an expression for the variance of this estimator is derived under mild conditions.

TL;DR: In this article, the authors consider the construction of nearest neighbor designs which satisfy the balance conditions of Wilkinson et al. (1983) and show that the balance condition can be satisfied by a number of authors.

TL;DR: In this article, a series of incomplete block designs for symmetrical parallel lines are proposed and important contrasts like L p, L 1 and L ′ 1 are estimated free from block effects.

TL;DR: In this paper, the minimum number of group tests necessary to specify the number of defective elements in a linearly ordered set L of cardinality n of which exactly d elements are defective is determined.

TL;DR: In this paper, a practical truncation procedure based on a test of hypothesis about the regression coefficient is suggested, and the properties of such a conditional estimator are studied and it is demonstrated that the suggested procedure removes the above mentioned disadvantage of the classical estimator.

TL;DR: In this article, a test of normality proposed by Lancaster (1969) is shown to have power comparable to that of other normality tests, and approximate formulae for critical values are given and the relation with a test given in Thomas and Pierce (1979) is discussed.

TL;DR: In this article, a method of construction of group divisible (GD) designs from a resolvable balanced incomplete block (BIB) design with new families is given, and new non-isomorphic solutions for regular GD designs are produced.

TL;DR: In this article, the maximum and average variance of the difference between estimated responses are taken as design criteria for univariate polynomial regression models, and an optimal design under the first criterion is derived for the second-order model and a class of designs nearly optimal under the second criterion is obtained for the general polynomials.