论文检索

截断参数的序贯估计AI 解读

Consider the problem of sequentially estimating the parameter θ of a uniform distribution on (0, θ). It is shown that if the loss is measured by squared error plus a linear cost function, and the prior on θ is given by a Pareto distribution, a simple heuristic procedure incurs an excess risk above the Bayes risk not greater than the cost of three observations. The result is extended to a wider class of distributions which includes the uniform and to a wide class of priors.

不完整数据裂区分析中的 Geisser–Greenhouse 校正注记AI 解读

Growth curve, wear curve, and repeated measurement experiments frequently are analyzed as split-plot designs with time used as the subplot treatment. This method is particularly convenient when the data have missing values in the repeated measurements since multivariate methods are not easily adapted to data with different dispersion matrices. This article establishes that the dispersion structure which guarantees that the subplot test ratio has an F distribution for…

若干非线性模型中的估计AI 解读

Extensions of linear model contrasts to general and location-scale models are proposed. These extensions are defined in terms of shift functions which measure how much the variables from one population must be shifted to be aligned in distribution with the variables from another. A general estimate based on empirical distribution functions and three estimates appropriate for the location-scale model are considered and compared in terms of asymptotic relative efficiencies. An…

有限总体抽样中的方差估计AI 解读

Under a linear regression model, the best linear unbiased estimator (BLUE) for a finite population total can be obtained. The problem studied here is that of estimating the variance for setting large-sample confidence intervals about the BLUE when the model generating this estimate is inaccurate. A robust variance estimator is derived, and its asymptotic properties are shown to compare favorably with those of the weighted least-squares variance estimator. The robust variance…

不完整数据判别分析的一致回归方法AI 解读

Modifications are proposed for a method of discriminant analysis with missing values described by Chan, Gilman, and Dunn (1976). The modified methods are special cases of techniques for handling missing values in multivariate linear regression. Less stringent conditions for when missing values are missing at random are suggested.

Box-Cox变换在受限因变量模型中的应用AI 解读

The general limited dependent variable model discussed in this article permits skewness in a pretruncated variable by transforming it within the class of Box-Cox transformations. As a by-product this general model also provides a convenient nesting framework for statistically distinguishing between numerous limited dependent variable models. An application to a model of the supply of bilateral foreign aid illustrates the ability of the general model to empirically…

回归中的季节性：平滑先验的应用AI 解读

This article argues that conventional approaches to the treatment of seasonality in econometric investigation are often inappropriate. A more appropriate technique is to allow all regression coefficients to vary with the season, but to constrain them to do so in a smooth fashion. A Bayesian method of estimating smoothly varying seasonal coefficients is developed, based on Shiller's (1973) approach to estimating distributed lags. In a sampling experiment, this technique…

随机区组设计中针对有序备择的无分布检验AI 解读

In this article we consider a class of test statistics that are useful for testing against ordered alternatives in balanced or unbalanced block designs. The approach consists of forming a statistic on each block and then combining the block statistics as a weighted sum to obtain one overall test statistic. Large-sample properties such as asymptotic normality and asymptotic relative efficiency as the number of blocks tends to infinity are considered. Throughout the article…

不等样本量下 Bartlett 方差齐性检验统计量的精确分布AI 解读

An expression is derived for the null density of the Bartlett test statistic for testing equality of variances of n normal populations, when random samples not necessarily of the same size are taken. The expression permits computation of exact Bartlett critical values. As a generalization, an expression is derived for the density of the normalized ratio of an arbitrarily weighted geometric mean to the unweighted arithmetic mean, based on a sample of n independently…

有限总体子总体均值的序贯置信区间AI 解读

Sequential confidence intervals for the parameters of a subpopulation of a finite population are studied. Procedures are suggested using the mean, median, and trimmed means; these procedures are shown to be more efficient than their counterparts which are based on independent, identically distributed observations from infinite populations. The major technique used is to “linearize” the estimates, yielding as a simple consequence proofs of central limit theorems. A Monte…

比较多个正态均值与指定标准的两种选择程序AI 解读

The problem of comparing k normal means with a specified (absolute) standard is considered. A single-stage and a two-stage (k + 1)-decision procedure are proposed for the cases of common known variance and common unknown variance, respectively. The procedures guarantee that (1) with probability at least P 0* (specified), no population is selected when the largest population mean is sufficiently less than the standard, and (2) with probability at least P 1* (specified), the…

自回归过程的重复测量AI 解读

Estimation of parameters and tests of hypotheses are studied in first-order autoregressive processes where the process is observed several times over a given time interval. The process may be homogeneous (i.e., the parameters may be constant over time) or inhomogeneous (time-varying parameters). Sufficient statistics under normality are obtained for various cases and several tests of hypotheses are given.

存在无应答时回归分析的样本量选择AI 解读

Assuming nonresponse, inference concerning the regression coefficients of a multiple linear regression is considered from a Bayesian viewpoint. We exploit a two-phase sampling scheme. At each phase the sample design is of the following type: Select a random sample of size n with n 1 responses obtained. Then, a subsample of size n 2(0 ≤ n 2 ≤ n — n 1) is selected from the n — n 1 nonrespondents. Assuming 100 percent response from the units in the subsample, the principal…

有限总体抽样与稳健估计AI 解读

The work of Royall and Herson (1973a, 1973b), ensuring the robustness of the standard ratio estimator against polynomial superpopulation models by choosing balanced samples, is extended to a more general regression estimator. The requirement for robustness is then a relationship between the moments of the sample units and those of the remainder of the population which may be achieved approximately by unequal probability sampling.

信息有限条件下的预测：平车载拖车运输市场的 ARIMA 模型AI 解读

This paper evaluates the appropriateness of autoregressive integrated moving average (ARIMA) time-series models for forecasting in information-scarce environments. Such environments are defined and a specific transportation sector example examined. It is shown that ARIMA models adequately characterize economic activity in this example. ARIMA model forecasts are seen to dominate alternative models, and to provide information required for market efficiency. Specific attention…

卡方拟合优度统计量实际检验水平的小样本比较AI 解读

The small-sample properties of three goodness-of-fit statistics for the analysis of categorical data are examined with respect to the adequacy of the asymptotic chi-squared approximation. The approximate tests based on the likelihood ratio and Freeman-Tukey statistics yield exact levels that are typically in excess of the nominal levels for moderate expected values. In contrast, the Pearson statistic attains exact levels that are quite close to the nominal values. The reason…

摘要暂缺

一种稳健的离散程度检验AI 解读

The simplicity and surprisingly good small-sample power properties of the ordinary sign test motivate its use, in suitably adapted form, as a dispersion test. The proposed test statistic is based on the number of observations lying more than a specified distance from the sample mean. For symmetric and moderately skewed distributions, the proposed test is robust and has good power properties.

有限总体中子总体均值的序贯置信区间AI 解读

Sequential confidence intervals for the parameters of a subpopulation of a finite population are studied. Procedures are suggested using the mean, median, and trimmed means; these procedures are shown to be more efficient than their counterparts which are based on independent, identically distributed observations from infinite populations. The major technique used is to “linearize” the estimates, yielding as a simple consequence proofs of central limit theorems. A Monte…

若干非线性模型中的估计AI 解读

Extensions of linear model contrasts to general and location-scale models are proposed. These extensions are defined in terms of shift functions which measure how much the variables from one population must be shifted to be aligned in distribution with the variables from another. A general estimate based on empirical distribution functions and three estimates appropriate for the location-scale model are considered and compared in terms of asymptotic relative efficiencies. An…

有限信息下的预测：铁路平车载拖车运输市场的 ARIMA 模型AI 解读

This paper evaluates the appropriateness of autoregressive integrated moving average (ARIMA) time-series models for forecasting in information-scarce environments. Such environments are defined and a specific transportation sector example examined. It is shown that ARIMA models adequately characterize economic activity in this example. ARIMA model forecasts are seen to dominate alternative models, and to provide information required for market efficiency. Specific attention…

回归中的季节性：平滑先验的应用AI 解读

This article argues that conventional approaches to the treatment of seasonality in econometric investigation are often inappropriate. A more appropriate technique is to allow all regression coefficients to vary with the season, but to constrain them to do so in a smooth fashion. A Bayesian method of estimating smoothly varying seasonal coefficients is developed, based on Shiller's (1973) approach to estimating distributed lags. In a sampling experiment, this technique…

截断参数的序贯估计AI 解读

Consider the problem of sequentially estimating the parameter θ of a uniform distribution on (0, θ). It is shown that if the loss is measured by squared error plus a linear cost function, and the prior on θ is given by a Pareto distribution, a simple heuristic procedure incurs an excess risk above the Bayes risk not greater than the cost of three observations. The result is extended to a wider class of distributions which includes the uniform and to a wide class of priors.

存在无应答时回归分析的样本量选择AI 解读

Assuming nonresponse, inference concerning the regression coefficients of a multiple linear regression is considered from a Bayesian viewpoint. We exploit a two-phase sampling scheme. At each phase the sample design is of the following type: Select a random sample of size n with n 1 responses obtained. Then, a subsample of size n 2(0 ≤ n 2 ≤ n — n 1) is selected from the n — n 1 nonrespondents. Assuming 100 percent response from the units in the subsample, the principal…