日期精度：到日 2575 篇 · 到月 3 篇 · 到年 0 篇
匹配分布的渐近结果
Summary The generalized matching distribution is investigated. A necessary and sufficient condition for asymptotic Poissonity is given. The case of two identical decks is given special attention.
滑移问题中一种序贯程序的性能
Summary The basic problem known as a “Slippage problem” is to decide that none of the k experimental categories is better than the control or decide that a certain category is better. In this paper, a class of asymptotically efficient sequential procedures is proposed when both the error probabilities are controlled at a specified level (see also Srivastava, 1966). Assuming that these populations are normal with unknown variance σ2, the performance of the sequential…
双变量检验与双重单变量检验的功效比较
Summary The paper describes a comparative study of the power of four bivariate tests of linear hypotheses and of a “twofold univariate” test equivalent to applying separate F-tests to the two variables. The powers of the multivariate tests are estimated by Monte Carlo methods, and that of the twofold univariate test is derived by a method using characteristic functions. Graphs describing the powers are given, leading to practical recommendations in terms of parameters which…
多元时间序列模型的参数估计
Summary We shall present a practical iterative method for estimating parameters in mixed autoregressive moving-average models for multivariate stationary time series. This method essentially generalizes that of Marquardt (1963) as applied by Box and Jenkins (1970) to univariate time series. We shall investigate the statistical properties of the method in order to demonstrate desirable convergence behaviour.
调查设计、对称性与后验分布
Summary It is now well known that the sample design is irrelevant in a Bayesian analysis of survey data provided the units are labelled and the sampling is non-informative. However, information about the labels is often not available for the analysis, and in this situation the design will contain information about the labelling and hence affect the inferences. There is one important exception: if the prior distribution is exchangeable and we are interested only in symmetric…
线性回归模型中自相关误差的一种新检验
Summary A test for autocorrelated errors in the linear model is introduced and shown to have, in general, greater power than the Durbin and Watson test for high values of autocorrelation.
多元似然比统计量分布的若干近似
Summary Some approximations, using χ 2 and F, are given for the distribution of the likelihood ratio statistic used for simultaneous testing of the mean and covariance of a multivariate normal distribution. Consideration is given to the accuracy of the proposed approximations.
一般贝叶斯线性模型
Summary Lindley and Smith (1972), using a hierarchical form of prior structure, derived Bayesian alternatives to least squares estimates for the linear model. This paper examines the Bayesian model in more detail and notes some general properties of the resulting estimators. Comparison is made with a least squares approach to models of the second kind, and an example is given.
傅里叶级数与球谐回归的极小极大设计：可旋转点配置的刻画
Summary In the framework of the approximate theory of the optimal design of experiments, Hoel (1965) represented minimax designs for Fourier series and spherical harmonics regressions of order r in terms of certain normalizing coefficients which are difficult to interpret. In this paper it is shown that these designs are intimately related to rotatable arrangements of points of order r in two and three dimensions, respectively. This result is used to construct exact minimax…
二元分布的拟合优度检验
Summary Tests of fit based on generalized minimum χ2 techniques are developed for bivariate distributions. The asymptotic null distribution of the test statistic is χ2 while the asymptotic non-null distribution turns out to be that of a weighted sum of independent non-central χ2 variates. The special case of testing the fit of a bivariate normal distribution is investigated in detail and the power is obtained for several alternative families of bivariate distributions.
泊松回归的贝叶斯与经典分析
Summary This paper is concerned with the problem of testing the existence of a trend in the means θi of Poisson distributions. It is assumed that these means are changing exponentially, that is, log θi = α + βxi. A classical method is reviewed which is used for testing the hypothesis β = 0. The exact Bayesian distribution for β is derived and a Bayesian approximation suggested which proved to be very useful. Finally, a comparison of these three methods by means of numerical…
多峰与轴向圆周总体的多样本检验
Summary We propose an l-modal c-sample non-parametric test U on a circle based on uniform scores. The test is derived with the help of an l-modal von Mises type distribution. Critical values of the distribution are given and the asymptotic distribution of U and its parametric competitor V are obtained. For the shift-type alternatives we derive Bahadur's efficiency of the U-test relative to the V-test and consider some particular cases. We also examine the small sample powers…
合并可能相关的估计问题
Summary We have two sets of parameters we wish to estimate, and wonder whether the James-Stein estimator should be applied separately to the two sets or once to the combined problem. We show that there is a class of compromise estimators, Bayesian in nature, which will usually be preferred to either alternative. “The difficulty here is to know what problems are to be combined together— why should not all our estimation problems be lumped together into one grand melée?”…
随机化模型下的协方差分析
Summary The randomization model for the analysis of covariance in a randomized block design is considered. Asymptotic properties of tests and estimates are obtained and it is shown that if the number of replicates is large, then the usual results concerning tests are approximately true. The large sample power of the tests are obtained and it is shown that using the concomitant variate increases the power.
节点数量未知时的贝叶斯样条回归
Summary The problem of selecting the model and coefficients for a spline regression curve with normal errors is considered. The locations of all possible knots are assumed to be known; which subset of these is the set of actual knots is unknown. Each subset forms a model. Priors of the form of a marginal distribution on the index of the model and a conditional distribution for each model on the coefficients and variance are allowed. The posterior distribution is explicitly…
Box–Jenkins 传递函数—噪声模型的贝叶斯估计
Summary The problem of estimating the coefficients of the transfer function-noise models proposed by Box and Jenkins is considered. A Bayesian approach is taken and the exact posterior density function of the coefficients is derived. Because of the complexity of this function, inference about individual parameters is virtually impossible except in the most simple cases. Accordingly, it is desirable to consider certain approximations. In particular, it is shown that inference…
两条回归曲线的相对位置
Summary In a non-singular bivariate Gaussian distribution the regression curve of y on x has smaller slope (measured by dy/dx) than the regression curve of x on y. Calling this the standard position and defining in a fairly obvious way a “clear-cut reversal” of it, we show that, for a distribution whose mean exists, such a reversal is impossible overall if the curves cross only once, and impossible at the extremities if the curves interlace in a more complicated way.…
使用样本分位数的拟合优度检验
Summary A goodness-of-fit test is constructed using sample quantiles for a p.d.f. F(x, θ) (where θ is to be estimated) which is continuous and strictly increasing at the quantiles of interest. It is shown to be asymptotically equivalent, under alternatives “close” to the null, to the usual goodness-of-fit test based on grouped observations, the advantage being that we may avoid the difficulties of choosing cell boundaries for grouping.
未知滞后长度的滞后回归
Summary The problem considered is that of determining the parameters in a lagged regression of one stationary time series on another when the lag is unknown and is not an integral multiple of the time interval between observations. The residual in the regression is also taken to be a stationary time series. The method of estimation is based on the maximization with respect to the lag of a form of autocorrelation between the two series. However, the autocorrelation is defined…
乘积型交互对比的同时置信区间
Summary The set of product-type interaction contrasts, which contains the subsets of interaction residuals, tetrad contrasts, double-dichotomy contrasts and pooled-tetrad contrasts, is discussed. In the Normal case with equal and known variances, simultaneous confidence intervals for a given set of such contrasts can be constructed in several ways. Five such methods (the Scheffé method, the Tukey method, the Dunn method, a method based on Roy's maximum-root statistic and a…
贝叶斯推断与结构推断中的边际化悖论
Summary We describe a range of routine statistical problems in which marginal posterior distributions derived from improper prior measures are found to have an unBayesian property—one that could not occur if proper prior measures were employed. This paradoxical possibility is shown to have several facets that can be successfully analysed in the framework of a general group structure. The results cast a shadow on the uncritical use of improper prior measures. A separate…
双变量非平稳过程的分析
Summary In this paper, we propose a general definition of the evolutionary (time-dependent) cross-spectrum between two non-stationary processes and describe its physical interpretation. We also study the estimation of the evolutionary cross-spectrum at each time instant t from a single realization of a bivariate process. Further, we propose a definition (and a method of estimation) for the coherency (spectrum) between the two components of the bivariate process and show that…
似然方法在含大量参数模型中的应用
J. D. Kalbfleisch, D. A. Sprott; Application of Likelihood Methods to Models Involving Large Numbers of Parameters, Journal of the Royal Statistical Societ
圆周数据的多样本均匀得分检验及其参数竞争检验
Summary We propose a c-sample non-parametric test W on a circle based on uniform scores. The test can be regarded as an extension of Wheeler and Watson's test (1964). This test is constructed with the help of a variant of a c-sample test for von Mises populations under the shift-type of alternatives. We indicate the relationship of the W-test with a test given by Mardia (1970). This result solves the problem of critical values of this test and of approximations to the null…