日期精度：到日 2258 篇 · 到月 2354 篇 · 到年 2207 篇
相关系数自助法估计的一则札记
Smoothed bootstrap estimation of the sampling standard deviation of the variance-stabilized correlation coefficient is reconsidered. An approximation to the mean squared error of the bootstrap estimator is obtained and an empirical procedure for choosing the degree of smoothing in the bootstrap estimation is presented. Performance of the procedure is examined in a simulation study.
回归变换得分检验的进一步讨论
Lawrance's (1987) results concerning tests for transformation in regression are extended to models where response and mean may both be transformed. It is also suggested (i) that the methods of Lawrance and of Atkinson (1982) lead to statistics with near-perfect correlation, and (ii) that observed and expected informations may have considerably different effects as standardizations of the score statistic.
重复测量临床试验中的序贯检验
In some clinical trials, the number of subjects on each treatment is fixed and at successive equally-spaced time points each subject yields a measurement which reflects response to treatment. A model is presented for such repeated measurements data. A sequential procedure is proposed for testing the null hypothesis of no difference in mean effect between two treatments. In this procedure, the maximum number of measurements per subject and absorption probabilities for…
二阶 Fisher 信息
The paper presents general second-order approximate formulae for the Fisher information of asymptotically normal statistics, and applies the formulae to a stationary time-series model as well as to an econometric simultaneous equation model. Also the second-order conditional information is evaluated for the exponential family and the location family. Conditioned on a second-order ancillary statistic, the second-order information loss of the maximum likelihood estimate is…
两个组的共同主成分子空间
One important practical application of principal component analysis is to reduce a large number of variables, say p, to a smaller number, m, by making use of the first m principal components. This technique can easily be extended to two or more groups if the subspaces spanned by the first m principal components are the same for all groups. In this paper we develop an approximate procedure for testing such a hypothesis of common subspaces when two groups are involved. The…
二项分布参数 N 的推断：层级贝叶斯方法
A hierarchical Bayes approach to the problem of estimating N in the binomial distribution is presented. This provides a simple and flexible way of specifying prior information, and also allows a convenient representation of vague prior knowledge. It yields solutions to the problems of interval estimation, prediction and decision making, as well as that of point estimation. The Bayes estimator compares favourably with the best, previously proposed', point estimators in the…
零方差比检验的稳健性与功效
A locally optimal test for a null variance ratio is considered in the context of the one-way random effects model, when normality is assumed. Using an asymptotic design sequence with an increasing number of groups with bounded but unequal sizes, this test has the correct asymptotic level of significance for nonnormal data, a property which is not shared by the competing Wald test. Asymptotic power calculations demonstrate that the locally optimal test may be more powerful…
对误差方差错设更稳健的标准误
SUMMARY For parameter estimators in linear models, variance estimates are proposed which are positive-semidefinite quadratic forms like the conventional ones but are less dependent on assumptions about error variance. Examples are given of their use in spatial analyses of field trials and analyses of series of trials.
非参数回归中残差方差的估计
A wide class of estimators of the residual variance in nonparametric regression is considered, namely those that are quadratic in the data, unbiased for linear regression, and always nonnegative. The minimax mean squared error estimator over a natural class of regression functions is derived. This optimal estimator has an interesting structure and is closely related to a minimax estimator of the regression curve itself.
简单随机流行病模型中感染率最大似然估计的近似
Hill & Severo (1969) and Kryscio (1972) present approximations to the maximum likelihood estimator of the infection rate of the simple stochastic epidemic model. These approximations, valid under some restrictions on the data set, use a table published by Hill & Severo (1969). We give here an algebraically simpler approximation, which does not use an auxiliary table and may be applied to all data sets.
基于修正 Bonferroni 检验的逐阶段拒绝多重检验程序
Simes (1986) has proposed a modified Bonferroni procedure for the test of an overall hypothesis which is the combination of n individual hypotheses. In contrast to the classical Bonferroni procedure, it is not obvious how statements about individual hypotheses are to be made for this procedure. In the present paper a multiple test procedure allowing statements on individual hypotheses is proposed. It is based on the principle of closed test procedures (Marcus, Peritz &…
Bartlett 调整后似然比统计量的检验水平误差
It is well that Bartlett adjustment reduces level-error of the likelihood ratio statistic from order n−1 to order n−3/2. In the present note we show that level-error of the adjusted statistic is actually order n−2.
稳健时间序列建模中的拟合优度检验
The problem of testing the adequacy of a time series model in the presence of outliers is considered. The classical portmanteau statistic is generalized to an important class of robust estimators. Some Monte Carlo results suggest that the proposed generalization possesses good robustness properties over the classical statistic. A robustified version of a result of Newbold (1980) is also obtained.
鱼类标记实验中自然死亡率估计的比较
Tagging experiments in which recaptures have to be made by professional fishermen are considered. The methods put forward are shown to be maximum likelihood solutions, and expressions are derived for the variances of the estimators. Optimal conditions for the experiment are found, and cases of questionable behaviour are identified.
时间序列回归中的单位根检验
This paper proposes new tests for detecting the presence of a unit root in quite general time series models. Our approach is nonparametric with respect to nuisance parameters and thereby allows for a very wide class of weakly dependent and possibly heterogeneously distributed data. The tests accommodate models with a fitted drift and a time trend so that they may be used to discriminate between unit root nonstationarity and stationarity about a deterministic trend. The…
左截断与右删失数据下失效率递增的生存函数估计
The maximum conditional likelihood estimator of the survival function with increasing hazard rate is derived, based on left truncated and right censored data. This estimator always exists, whereas the fully nonparametric conditional maximum likelihood estimator may not exist. A strong consistency theorem is established based on the total time on test transformation.
调查抽样中基于模型推断的条件化问题
A ‘discontinuity’ of sampling distribution inference between a prediction problem and an estimation problem in model-based survey sampling is discussed. The problem is resolved by conditioning on an appropriate ancillary within a curved exponential family framework. The ignorability of the sampling design for inference is discussed.
实参数的条件推断：样本空间上的微分方法
A one-dimensional conditional procedure defines a partition of the sample space into curves which can be represented by means of a unit vector field. A formula is given for the conditional distribution in terms of local properties of the vector field. Conditions are developed for reducing the first-order effects of nuisance parameters and reproducing to higher order the likelihood change for the parameter of interest. The emphasis is on extending exponential family methods…
单个统计泛函的经验似然比置信区间
The empirical distribution function based on a sample is well known to be the maximum likelihood estimate of the distribution from which the sample was taken. In this paper the likelihood function for distributions is used to define a likelihood ratio function for distributions. It is shown that this empirical likelihood ratio function can be used to construct confidence intervals for the sample mean, for a class of M-estimates that includes quantiles, and for differentiable…
具有负二项变异的计数数据单因素分析
Two C(α) statistics (Neyman, 1959) for testing the equality of the means of several groups of count data in the presence of a common dispersion parameter are derived. The performance of the two C(α) statistics, the likelihood ratio statistic and two more statistics based on transformed data (Anscombe, 1948) is then compared in terms of size and power by using Monte Carlo simulations. The C(α) statistics are recommended. The C(α) statistics for testing the equality of the…
相对风险回归的残差
Several possible definitions of residuals are given for relative risk regression with time-varying covariates. Each such residual has a representation as an estimator of a stochastic integral with respect to the martingale arising from a subject's failure time counting process. Previously proposed residuals for individual study subjects and for specific time points are shown to be special cases of this definition, as are previously derived regression diagnostics. An…
利用重复观测估计权重的加权最小二乘渐近理论
SUMMARY We consider a heteroscedastic linear regression model with replication. To estimate the variances, one can use the sample variances or the sample average squared errors from a regression fit. We study the large-sample properties of these weighted least-squares estimates with estimated weights when the number of replicates is small. The estimates are generally inconsistent for asymmetrically distributed data. If sample variances are used based on m replicates, the…
线性回归模型的似然推断
Approximate conditional inference based on large-sample likelihood ratio methods is considered for the parameters of linear regression models. Mean and variance adjustments that improve the standard normal approximation to the conditional distribution of the signed square root of the log-likelihood-ratio statistic for a scalar parameter of interest are given. A Bartlett adjustment factor that improves the chi-squared approximation to the conditional distribution of the…
基于剖面似然的区间估计：强拉格朗日理论及判别应用
Strong Lagrangian theory is used to illuminate the properties of the profile log likelihood. General conditions are given which lead to a simplification of the computations required to plot this function or calculate interval estimates based upon it. The results presented are rather general with a variety of possible applications. In particular, it is shown that they provide a simple solution to the important practical problem of obtaining an interval estimate for the…