Journal•ISSN: 0008-0683

# Calcutta Statistical Association Bulletin

About: Calcutta Statistical Association Bulletin is an academic journal. The journal publishes majorly in the area(s): Estimator & Population. It has an ISSN identifier of 0008-0683. Over the lifetime, 979 publication(s) have been published receiving 5157 citation(s).

##### Papers published on a yearly basis

##### Papers

More filters

••

171 citations

••

TL;DR: A balanced incomplete block design with parameters, v, b, r, k,.\\ is said to be resolvable if the blocks of a design are separable into r sets of n blocks each as mentioned in this paper.

Abstract: 1. A balanced incomplete block design with parameters, v, b, r, k, .\\ is said to be resolvable if the blocks of a design are separable into r sets of n blocks each (implying b=nr) in such a way that each variety occurs only once among the n blocks of a set forming a complete replication (obviously v=nk). Bose ( 1942 ) has proved a number of relations obtaining among the parameters of a resolvable design. The important ones are as follows :-

119 citations

••

TL;DR: In this paper, the authors study the differeut properties of the F-test which point out its merits and demerits from the point of view of errors of the first and second kind.

Abstract: The technique of analysis of variance is a powerful statistical tool in tracing the sources of variation of an observed random variable to different assignable causes. But the ease of calculations and the readily available F-test have made possible its somewhat uncritical applications in some cases. As a test of significance it should, however, derive its justification from the measure of control · it might effect over errors of different types involved ; and this has to be realised all the more because this test very often precedes any detailed analysis of the results. As for example, in judging the differences between the yields of a number of varieties of any particular crop, say rice, first of all we apply a comprehensive F-test embracing all the varieties simultaneously, and only when this comes out to be significant we proceed to analyse the individual differencesi. Hence there is the need of investigating whether the commonly applied F-test takes adequate account of the individual differences and whether any alternative procedure might appear to be better in particular situations. In this article we study the differeut properties of the F-test which point out its merits and demerits f . cm the point of view of errors of the first and second kind and v. hich also wggest a useful modification of the analysis of variance procedure for certain types of problems. For this purpose we will consider throughout the following simpler formulation (i.e. canonical form) of the problem, and at the

114 citations

••

113 citations

••

TL;DR: In this article, a general class of rank order tests for progressive censoring is proposed along with a basic martinga:le property and a Brownian motion approximation for a related rank order process, asymptotic distribution theory of the proposed statistics is developed.

Abstract: SummaryProgressive censoring schemes (allowing a continuous monitoring of experimentation until a terminal decision is reached) are often adopted in clinical trials and life testing problems. In this paper, a general class of rank order tests for progressive censoring is proposed. Along with a basic martinga:le property and a Brownian motion approximation for a related rank order process, asymptotic distribution theory of the proposed statistics is developed. Asymptotic performance characteristics of the proposed tests (in the light of Bahadur efficiency and the stochastic smallness of the stopping variables) are studied.

88 citations