论文检索

摘要暂缺

不完整数据下期望意义中新优于旧性质的检验AI 解读

This article proposes a test for the problem of testing that a life distribution is an exponential distribution against the alternative that it is new better than used in expectation, not exponential, on the basis of randomly right censored data. The test statistic is an analog of the “total time on test” test statistic.

多元位置参数的一类稳健检验与估计AI 解读

Hotelling's T 2 test and the sample mean vector for multivariate location suffer from the same lack of robustness as the univariate t test and sample mean. We propose a class of tests and estimates based on a vector of rank statistics and show that they are easy to compute, have good robustness properties, and are usually more efficient than the classical procedures.

提高负二项分布与Neyman A型分布拟合检验功效的方法AI 解读

A modification of the quadratic form involved in a generalized minimum chi-squared procedure yields the same asymptotic null distribution of the test statistic for testing fit by an assumed model, but a different form of nonnull distribution emerges. This result is applied to testing fit of the negative binomial and Neyman Type A distributions, and tables of asymptotic power are presented that show the increase of power obtained. A numerical example is presented to…

一类岭回归估计量的频率学派分析AI 解读

We discuss ridge regression estimators as a class, showing how six recently proposed estimators can thus be viewed, and give reasons for preferring one of these (empirical Bayes maximum likelihood estimator) to the other five. Results are based on analysis rather than simulations and on a frequentist rather than Bayesian viewpoint.

逆高斯分布方差及其倒数的一致最小方差无偏估计AI 解读

The two-parameter inverse Gaussian distribution is found to have useful applications in a wide variety of fields. The uniformly minimum variance estimator of its mean is known and is the sample mean; however, no such estimator of the variance is reported in the literature. Here the uniformly minimum variance unbiased estimators of the variance and its reciprocal are derived.

基于 Wilcoxon 型统计量的分类规则的渐近性质AI 解读

Suppose training samples are available from two location parameter populations. Nonparametric classification rules based on Wilcoxon-type statistics are defined. The efficiencies of the nonparametric rules relative to the “optimal” estimated parametric rules are then investigated by using asymptotic expansions of the probabilities of misclassification.

不等概率抽样中 Yates–Grundy 方差估计量的不可容许性AI 解读

An example is given to show that there exist fixed sample size designs for any sample size greater than two, for which the Yates-Grundy estimator is inadmissible in the class of nonnegative unbiased quadratic estimators of the variance of the Horvitz-Thompson estimator. A necessary condition for the Horvitz-Thompson variance estimator to be nonnegative definite is pointed out. It is also pointed out that a posterior lower bound can be obtained for any nonnegative definite…

线性函数关系与联立方程中估计量分布的渐近展开AI 解读

We derive asymptotic expansions of the distributions of the maximum likelihood (ML) estimator and the ordinary least squares (OLS) estimator in a linear functional relationship model as the sample size increases infinitely. These expansions are equivalent to the asymptotic expansions of the distributions of the limited information maximum likelihood (LIML) estimator when the covariance is known to within a proportionality constant and the two-stage least squares (TSLS)…

通过最小分量识别有序二元正态分布AI 解读

For full-rank covariance matrix and other subfamilies of the ordered bivariate normal distribution, the identifiability of parameters by the minimum variate is demonstrated. For the general family, the distribution is not identified. These identifiability questions arise in connection with estimation within certain econometric models, for example, Tobin and Fair-Jaffee.

右删失下两样本问题的条件分布无关检验AI 解读

Two-sample rank tests for survival data in the presence of arbitrary right censoring are considered. We distinguish between administrative censoring, arising because survival study participants do not enter as a cohort, and censoring due to “loss to follow-up.” We show how conditionally distribution-free tests can be constructed in certain situations. Conditional versions of the generalized Wilcoxon and Mantel statistics are shown to be asymptotically normal in the…

任意右删失配对观测的广义 Gehan–Gilbert 检验AI 解读

An asymptotically distribution-free test, along the line of Gehan (1965) and Gilbert (1962), for paired observations that are subject to arbitrary right censorship is proposed. This test is shown to be more powerful than the sign test under a bivariate exponential model.

针对受限备择检验分布假设的 Pearson 卡方分量AI 解读

Motivated by the problems of detecting skewness and heavy tails in hypothetically normally distributed data, partially ordered families of alternative distributions are developed, the orderings being chosen to reflect skewness and tail weight. Optimal components of Pearson's X2, optimal in a minimax sense for detecting alternatives of this kind, are presented and their properties are discussed. Alternative approaches to the problem are also briefly discussed.

最小距离与稳健估计AI 解读

Robust and consistent estimation of the location parameter of an asymmetric distribution and general, nonlocation and scale parameter estimation problems have been vexing problems in the history of robustness studies. The minimum distance (MD) estimation method is shown to provide a heuristically reasonable mode of attack for these problems, which also leads to excellent robustness properties. Both asymptotic and Monte Carlo results for the familiar case of estimation of the…

Markowitz 有效投资组合的估计AI 解读

Given a set of N assets a portfolio is determined by a set of weights xi, i = 1, 2, …, N; Σ N i=1 xi = 1 indicating the proportion of the value of the portfolio devoted to each asset. A Markowitz efficient portfolio is the vector of weights X m that minimizes the variance σ m 2 of the total return from the portfolio, subject to the condition that the portfolio mean premium return μ m has a certain value. The estimators for the N × 1 vector X m , the return premium μ m , and…

月度时间序列中的日历效应：谱分析与图形检测AI 解读

Many time series, particularly national business and economic series, which are reported monthly and represent a total of the series for each month, contain calendar effects due to changing month length, weekly periodicities, and holidays. It is important to detect and remove this spurious calendar variation to allow a better appreciation of the variation in the series due to important factors. This article discusses detection. Two sets of diagnostic methods for detecting…

自然参数的广义贝叶斯估计量刻画AI 解读

Let X be a real-valued random variable with a family of possible densities (with respect to σ-finite μ) belonging to a one-parameter exponential family with the natural parameter θ ∈ Ω = natural parameter space. Let C(μ) = convex hull of the support of μ. Fix x 0> in the interior of C(μ), then δ is generalized Bayes for θ (with squared error loss) if and only if g(t) = exp { f 0 t δ(y + x 0)dy} (< ∞ for t + x 0 ∈ C(μ)) is a moment-generating function for a probability…

诊断与测量误差对事件概率估计的影响AI 解读

This article investigates the effect of misclassification and measurement error in the basic data on the asymptotic bias and efficiency of the logistic regression (LR) and normal discrimination (ND) classification procedures. The effect of misclassification in a single binary independent variable on the bias and efficiency of both procedures is also presented. Typically, asymptotic bias increases and efficiency decreases as misclassification and measurement error increase.…

变异系数相同但未知的两个正态总体的极大似然估计AI 解读

Maximum likelihood estimates are derived for the parameters of two normal populations with coefficients of variation equal but unknown. Formulas are provided for calculating the asymptotic variances and covariances of the estimates. The relative efficiency of the proposed mean estimator with respect to the sample mean is shown to be greater than one. The effect of departures from the assumptions of normality and of equal coefficients of variation on this relative efficiency…

简单变量测量误差模型的工具变量估计AI 解读

Alternative instrumental variable estimators for the slope in the simple errors-in-variables model are discussed. The maximum likelihood estimator is derived for the model in which the error covariance is known to be zero and for the model in which the error covariance is unknown. Modified maximum likelihood estimators and randomly weighted average estimators similar to those studied by Huntsberger are discussed. The limiting distributions of the estimators are presented and…

非正态总体下非平衡随机效应模型中F比的零假设与备择分布近似AI 解读

In this article we consider the unbalanced random-effects model as given in (1.1) with random variables from nonormal universes. Assuming that the αi 's are independently distributed of the eij 's, an approximation to the joint distribution of the mean squares (and hence the F ratio) by using Laguerre polynomials is derived. These results are then used to examine the effects of departure from normality on the traditional F-ratio distribution.

摘要暂缺

稳健非线性数据平滑算法的定义与比较AI 解读

Nonlinear data smoothers provide a practical method of finding smooth traces for data confounded with possibly long-tailed or occasionally spikey noise. They are resistant to the effects of extreme observations that are not part of the local pattern, yet they are able to respond rapidly to well-supported patterns. This article defines a collection of nonlinear smoothers based upon running medians and presents methods for describing and comparing their performance. The…

多变量 Portmanteau 综合检验统计量AI 解读

Box and Pierce have derived a goodness-of-fit test, the portmanteau test, for univariate autoregressive moving-average (ARMA) time series models. This test is here extended to multivariate ARMA models; the test statistic may be conveniently expressed as a function of the covariances between the residuals of the fitted model. A modified form of the statistic designed to have superior properties in small samples is derived, and the two forms of the statistic are compared via…