日期精度：到日 2274 篇 · 到月 7743 篇 · 到年 0 篇
删除极端观测对后 Kendall 秩相关估计量的偏差
This article obtains the average effect on the estimator of Kendall's rank correlation coefficient when extreme pairs are removed from a sample. Formulas, which are functions of Sterling numbers of the second kind, are derived for this bias. The exact bias, and an approximation, are tabulated for n = 3(1) 19.
不完全区组设计中区组间与区组内合并估计的精确方差
This article presents methods for evaluating exact variance of combined inter- and intra-block estimates of treatment effects in incomplete block designs. The results are valid for all incomplete block designs and hold for a wide class of combined estimates including most in the literature. Tables of exact variance for some estimates are presented for some balanced designs and for some partially balanced designs.
统计推断中的稳定分布（二）：稳定分布样本的信息
Large-sample theory for the estimation of parameters for a stable distribution is developed using the theory of Fisher's information. The asymptotic standard deviations and correlations of the maximum-likelihood estimates of the index, skewness, scale and location parameters are computed and tabled and used to compute the relative asymptotic efficiency of other proposed estimators. It is shown that if the true distribution is symmetric stable, the MLE's of index and scale…
残差的最优性：普通、加权与有偏最小二乘的比较
In the general linear model with observations not necessarily uncorrelated or homoscedastic, Gauss-Markov regression coefficients are superior to ordinary unweighted least squares in the well known BLU sense if the model is correct. However, it is shown that there is a weaker, but always applicable, minimum overall mean squared error sense in which Gauss-Markov residuals and biased residuals are inferior to ordinary least squares residuals as estimators of possible…
判别分析中构造渐近最优分配规则的迭代重分类程序
The construction of a suitable rule of allocation in the two-population discrimination problem is considered in the case where there are initially available from the populations II1, II2, n 1, n 2 observations and M unclassified observations. An iterative reclassification procedure based on the n 1 + n 3 + M observations is proposed and found asymptotically optimal when M → ∞ and n 1 and n 2 are moderately large. The case of finite M is evaluated by a Monte Carlo experiment…
自适应心理测验中二元响应的贝叶斯序贯程序
This article is concerned with a generalization of the problem of estimation of median effective dose in bioassay with a normal quantal response curve. A new kind of Bayesian motivated procedure is introduced which leads to a strongly consistent estimator. The convergence is robust in that it holds for a bundle of sequences of design vectors—an important feature in a mental testing context where a specified design vector cannot be produced on demand.
Behrens–Fisher 问题的两阶段程序
We consider the problem of constructing a fixed-width confidence interval for the difference between the means of two normal populations with unknown variances. A Stein-type two-stage procedure is presented and some of its properties are investigated. It is shown that the procedure is generally more efficient than Chapman's [1] solution.
给定检验强度下的最优双重抽样检验：正态分布
For a normally distributed random variable with unknown mean θ and known variance, optimum double sampling tests of strength (θ1, α, θ2, β) are found and compared with the single sampling test and the SPRT of the same strength. Two optimality criteria are used—minimax ASN and Bayes ASN. Tables of these optimum tests are given. Approximations to optimum double sampling tests for Poisson and binomially distributed variables are discussed.
含随机协变量的 Friedman 检验多元扩展
This article investigates a nonparametric procedure for testing for no treatment differences in multivariate two-way layouts with random covariates. The method is an extension of the Friedman χ r 2-test. Permutation and asymptotic permutation distributions are given and various asymptotic relative efficiency results are presented. An example illustrates the method.
损失函数未完全指定时的多个位置参数估计
If p ≥ 3 separate normal means are to be estimated, the usual, invariant estimator is “inadmissible” if the p separate loss functions can be pooled into a single loss function for the ensemble-of-means problem. Here, we formulate a version of the problem where the losses cannot be pooled in this way, and find a surprisingly weak necessary and sufficient condition under which the usual estimator is inadmissible in a sense appropriate to this formulation. We also examine the…
若干岭型估计量的蒙特卡洛评估
Consider the standard linear model . Ridge regression, as viewed here, defines a class of estimators of indexed by a scalar parameter k. Two analytic methods of specifying k are proposed and evaluated in terms of mean square error by Monte Carlo simulations. With three explanatory variables and determined by the largest eigenvalue of the correlation matrix, least squares is dominated by these estimators in all cases investigated; however, mixed results are obtained with…
可能含一个已标识异常观测时的期望寿命改进估计
A modified life testing model is defined where the sample contains at most one “identified” spurious observation whose expected life is greater than that of the others which form a homogeneous group. Various estimators of the smaller expected life are considered and definitive preference relationships among them are established using the mean squared error criterion. The case where the expected life of the spurious observation is smaller than that of the others is also…
线性模型中的异方差方差估计
We describe an estimator of heteroscedastic variances in the Gauss-Markov linear model where E(ε) = 0 and with σ i 2 and unknown. It may be thought of as an approximation to the MINQUE method which results in computational economy, positive estimates, and decreased mean square error. Properties of this almost unbiased estimator are stated. It is compared with other estimators, and extensions to more general models are discussed.
已知状态数量的切换回归模型：贝叶斯分析
Some aspects of Bayesian methods of inference relative to switching regression models are analyzed. It is shown that Bayesian confidence intervals and tests may be obtained by using Student's t and χ2 distributions. Mean biases and MSE of some Bayesian estimates are compared by Monte Carlo methods with those of the ML estimate. The MSE of the Bayesian estimates were uniformly smaller than those of the ML estimate. An experiment designed by Quandt [11] is also analyzed.
比较两个正态方差或两个伽马均值的统计表
Tables for constructing the uniformly most accurate unbiased confidence interval of level 1 − α for σ1 2/σ2 2, where σ1 2 and σ2 2 are the variances of two normal distributions, and for tests of level α of hypotheses specifying the value of σ1 2/σ2 2 are given for α = .1, .05, .01, .001, n 1,n 2 = 1(1)20(2)30, 36, 45, 60, 90, 180, ∞, where ni is the degree of freedom of the estimate of σi 2. The present tables, more accurate than previous ones, may also be applied to make…
预测中的样本重复利用方法及其应用
An account is given of a recently devised method of prediction based on sample reuse techniques. It is most useful in low structure data paradigms that involve minimal assumptions. A series of applications demonstrating the technique is presented.
使用 Stein 估计量及其推广进行数据分析
In 1961, James and Stein exhibited an estimator of the mean of a multivariate normal distribution having uniformly lower mean squared error than the sample mean. This estimator is reviewed briefly in an empirical Bayes context. Stein's rule and its generalizations are then applied to predict baseball averages, to estimate toxomosis prevalence rates, and to estimate the exact size of Pearson's chi-square test with results from a computer simulation. In each of these examples,…
残差最优性：普通、加权与有偏最小二乘的比较
In the general linear model with observations not necessarily uncorrelated or homoscedastic, Gauss-Markov regression coefficients are superior to ordinary unweighted least squares in the well known BLU sense if the model is correct. However, it is shown that there is a weaker, but always applicable, minimum overall mean squared error sense in which Gauss-Markov residuals and biased residuals are inferior to ordinary least squares residuals as estimators of possible…
判别分析中构造渐近最优分类规则的迭代重分类程序
The construction of a suitable rule of allocation in the two-population discrimination problem is considered in the case where there are initially available from the populations II1, II2, n 1, n 2 observations and M unclassified observations. An iterative reclassification procedure based on the n 1 + n 3 + M observations is proposed and found asymptotically optimal when M → ∞ and n 1 and n 2 are moderately large. The case of finite M is evaluated by a Monte Carlo experiment…
自适应心理测验中二元反应的贝叶斯序贯程序
This article is concerned with a generalization of the problem of estimation of median effective dose in bioassay with a normal quantal response curve. A new kind of Bayesian motivated procedure is introduced which leads to a strongly consistent estimator. The convergence is robust in that it holds for a bundle of sequences of design vectors—an important feature in a mental testing context where a specified design vector cannot be produced on demand.