摘要:

SummaryAn easily programmed recursive formula for the evaluation of the distribution function of ratios of linear combinations of independent exponential random variables is developed. This formula is shown to yield the probability that one team beats another in a contest we call the special gladiator game. This game generates tournaments which exhibit nontransitive dominance and have some surprising consequences. Similar results are obtained for a recursive formula based on the geometric distribution.

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1984.tb01224.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

SummaryDey (19711, Saha (1975), Kageyama&Saha (1983) and others have shown how optimum chemical balance weighing designs can be constructed from the incidence matrices of balanced incomplete block (BIB) designs. In this paper, it is shown that weighing designs can be constructed from some suitably chosen two‐symbol balanced arrays of strength two, which need not always be incidence matrices of BIB designs. The findings lead us to construct new optimum chemical balance weighing designs from incidence matrices of BIB design

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1984.tb01225.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

SummaryThe parameteric tests for equality of variance are well known. The classical F‐test is typically used to test the hypothesis of equality of two variances, while tests such as those developed by Bartlett (1937) are commonly used for the k‐sample hypothesis. These tests assume an underlying normal distribution and are quite sensitive to departures from normality (Box, 1953). Thus, when considering data that are from non‐normal distributions, alternative nonparametric tests must be employed.Fligner (1979) has proposed a class of two‐sample distribution‐free tests which possess very desirable properties and are attractive alternatives to other nonparametric tests for scale. The present paper extends the Fligner class of tests to the more general k‐

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1984.tb01226.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

SummaryFor a group of split‐plot designs it is assumed that the error variance is constant for a particular experiment but it varies from experiment to experiment. Assuming error variances to be known, estimators of the treatment parameters are obtained by weighted (generalised) least squares method and the corresponding analysis is given. For unknown error variances, an adjustment of the statistics using estimated weights is proposed for removing much of the resulting bias. The adjustment stems from a theorem due to Meier (1953

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1984.tb01227.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

SummaryA set of three goodness‐of‐fit procedures is proposed to investigate the adequacy of fit of Fisher's distribution on the sphere as a model for a given sample of spherical data. The procedures are all based on standard tests using the empirical distribution funct

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1984.tb01228.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

SummaryIdentified types of extreme value distributions are obtained from a basic form by variable transformation or truncation. The truncated distribution form is naturally generated as the extreme of a Poisson process with a randomly distributed size of each point event. If the size has a Negative Exponential distribution then, for moderate rates of the Poisson process, the extreme value distribution is of the type often called the Gumbel distribution. A Pareto distribution of size gives a second type which has natural association with a recurrence process of threshold exceedance.This specification of the extreme value distribution generates the identified distribution types in terms of physically meaningful parameters. The natural two parameter format provides the basis for a three parameter model which allows a more realistic description of the distribution of event sizes.Extreme values are often associated with data censoring due to some observations being out of range. Equations are given which demonstrate the simple association between estimators of the physically meaningful parameters in censored and uncensored situations.

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1984.tb01229.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

SummaryThis paper examines the joint statistical analysis of M independent data sets, the jth of which satisfies the model λjYj=XjB +εj, where the λjare unknown and the εiare normally distributed with a known correlation structure. The maximum likelihood equations, their asymptotic covariance matrix, and the likelihood ratio test of the hypothesis that the λjs are all equal are derived. These results are applied to two exam

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1984.tb01230.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

SummaryA two dimensional autoregressive moving average spatial model is used to analyse spatial interaction. Maximum likelihood estimates of the unknown parameters are derived as the solution of a system of nonlinear equations, and are shown to be best asymptotic normal. One important computational procedure is discussed. The argument is extended to the general regression model with autoregressive moving average residuals. Explicit computational formulae are given.

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1984.tb01231.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

SummaryThis paper deals with the problem of analysing the change over design in the context of a first order autoregressive process for the error terms. The method of maximum likelihood has been adopted for estimating treatment effects. The conditions derived for obtaining a balanced change over design show that a change over design balanced in the absence of autocorrelation is not necessarily balanced in the presence of autocorrelation. Also, it is observed that the autocorrelation co‐efficient and the treatment effect when p≠0 can be tested as usual with the likelihood ratio test criter

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1984.tb01232.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

SummaryAny order‐invariant function of a sequence of sample values may be expressed as a functional of the sample's empiric distribution function. This suggests that a very general approach to the theory of functions of sample values can be based on the empiric distribution function. The Komlós‐Major‐Tusnhdy (KMT) approximation provides a remarkable, mathematically tractable representation for the empiric distribution function of a random sample. Our aim in this paper is to describe the KMT approximation, particularly as it relates to other forms of approximation, and to survey some of its many applic

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1984.tb01233.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY