最大似然估计的一个推广

我们常常会遇到最大似然估计不存在的情况,这种情况以在非正态回归模型中最为典型。当参数向量不能被估计时,人们对参数向量的线性函数的估计饶有兴趣。本文给出了这些线性函数的广义最大似然估计的定义,讨论了它的性质,并得到了利用投影变换确定具有有限广义最大似然估计的线性函数的方法。最后,通过几个常见的定性资料统计模型的实例,展现了求广义最大似然估计的实施过程。     

向量参数的线性函数之广义最大似然估计

最大似然估计不存在的情况在非正态回归模型中最为典型,当参数向量不能被估计时,人们对参数向量的线性函数的估计饶有兴趣。本文给出了这些线性函数的广义最大似然 定义,建立了一些关于凹目标函数的结果,对某些特殊的目标函数,提供了求广义最大似然估计的具体途径,并详细地考虑了Ｃｏｘ的生存时间分析的模型。     

非线性回归模型的经验似然诊断

经验似然方法已经被广泛用于线性模型和广义线性模型.本文基于经验似然方法对非线性回归模型进行统计诊断.首先得到模型参数的极大经验似然估计;其次基于经验似然研究了三种不同的影响曲率度量;最后通过一个实际例子,说明了诊断方法的有效性.     

缺失数据下双重广义线性模型的参数估计

在经济领域和工业产品质量改进试验中,对均值和散度同时建模十分必要;在数据采集过程中,时常会遇到数据缺失问题.文章基于上述两点,研究缺失数据下的双重广义线性模型的参数估计,采用最近距离插补和反距离加权插补对缺失数据进行处理,并应用最大扩展拟似然估计和最大伪似然估计两种估计方法对未知参数进行估计.随机模拟和实例结果表明,该模型和所应用的方法是有用和有效的.     

拟似然非线性模型中MQLE的弱相合性的充分条件

拟似然非线性模型包括广义线性模型作为一个特殊情形.给出了拟似然非线性模型中极大拟似然估计的弱相合性的一些充分条件,其中矩的条件要弱于文献中极大拟似然估计的强相合性的条件.     

基于经验似然的部分线性模型的统计诊断

经验似然方法己经被广泛应用于许多模型的统计推断.本文基于经验似然对部分线性模型进行统计诊断.首先给出模型的估计方程,进而得到模型参数的极大经验似然估计;其次,基于经验似然研究了三种不同的影响曲率;最后通过随机模拟和实例分析,说明了统计诊断方法的有效性.     

正态总体均值与标准差比在简单半序约束下的最大似然估计

本文考虑两个正态总体均值和方差是未知参数,均值与标准差的比在简单半序约束下,且样本个数不同时,计算均值和标准差的最大似然估计的问题.给出了计算均值和标准差的最大似然估计的方法.同时还给出了三个总体均值与标准差的比在简单半序约束下求均值和标准差的最大似然估计的计算方法,并给出了迭代算法的模拟结果.     

缺失数据下双重广义线性模型的经验似然推断

本文基于截面经验似然的方法,在响应变量随机缺失时,将双重广义线性模型的拟似然估计方程作为截面经验似然比函数的约束条件,构造了均值模型和散度模型未知参数的置信区间.数据模拟中,在完全数据集,逆概率加权填补所得的数据集和未加权填补所得的数据集三种情形下,将经验似然方法与正态逼近方法相比较.结果表明在双重广义线性模型中,逆概率加权这一填补方法和经验似然方法是有效和可行的.     

Gamma恒定应力加速寿命试验的统计分析

证明了基于恒定应力加速寿命试验数据Gamma模型参数的最大似然估计在一定条件下存在,进而导出了Gamma模型参数的备择估计.利用Cornish-Fisher展开导出了Gamma形状参数的近似置信区间,另外也给了Gamma模型的其它参数和正常应力水平下产品寿命的一些重要可靠性指标的广义置信区间.利用模拟方法研究了所给点估计和区间估计的精度,模拟结果显示所给点估计和区间估计的精度是相当好的.     

非线性模型中的拟似然估计和约束拟似然估计

该文证明了,在非线性回归模型中,若以均方误差或均方误差矩阵为标准,拟似然估计是正则广义拟似然估计类中的最优估计,并讨论了拟得分函数最优性与拟似然估计最优性的关系.为改进拟似然估计,该文提出了一种约束拟似然估计,并证明了约束拟似然估计比拟似然估计有较小的均方误差.     

The importance of identifying different components of a mixture distribution in the prediction of field returns

Data from a mixture of distributions with two different increasing hazard functions can behave, over some period of time, like a distribution with decreasing hazard functions. As a result, reliability predictions based on data from a mixture of units with two or more different physical designs could be seriously wrong if the pooled data are used to extrapolate in time. Thus, it is important to identify components of the mixture and do statistical inference based on the stratified data. In this paper, the importance of this principle is investigated analytically and illustrated with lifetime data on high‐voltage power transformers. From engineering knowledge, the lifetime distribution of a transformer has an increasing hazard due, largely, to insulation aging. However, data from a population of units could indicate a decreasing hazard due to a mixture of units with different designs or environmental conditions. Comparisons are made between the predictions based on the pooled‐data and stratified‐data models and the importance of correct stratification in practice is shown. Some suggestions for practitioners are also given. Copyright © 2010 John Wiley & Sons, Ltd.     

Bayesian and likelihood inference from equally weighted mixtures

Equally weighted mixture models are recommended for situations where it is required to draw precise finite sample inferences requiring population parameters, but where the population distribution is not constrained to belong to a simple parametric family. They lead to an alternative procedure to the Laird-DerSimonian maximum likelihood algorithm for unequally weighted mixture models. Their primary purpose lies in the facilitation of exact Bayesian computations via importance sampling. Under very general sampling and prior specifications, exact Bayesian computations can be based upon an application of importance sampling, referred to as Permutable Bayesian Marginalization (PBM). An importance function based upon a truncated multivariatet-distribution is proposed, which refers to a generalization of the maximum likelihood procedure. The estimation of discrete distributions, by binomial mixtures, and inference for survivor distributions, via mixtures of exponential or Weibull distributions, are considered. Equally weighted mixture models are also shown to lead to an alternative Gibbs sampling methodology to the Lavine-West approach.     

An Extension of Generalized Linear Models to Finite Mixture Outcome Distributions

Finite mixture distributions arise in sampling a heterogeneous population. Data drawn from such a population will exhibit extra variability relative to any single subpopulation. Statistical models based on finite mixtures can assist in the analysis of categorical and count outcomes when standard generalized linear models (GLMs) cannot adequately express variability observed in the data. We propose an extension of GLMs where the response follows a finite mixture distribution and the regression of interest is linked to the mixture’s mean. This approach may be preferred over a finite mixture of regressions when the population mean is of interest; here, only one regression must be specified and interpreted in the analysis. A technical challenge is that the mixture’s mean is a composite parameter that does not appear explicitly in the density. The proposed model maintains its link to the regression through a certain random effects structure and is completely likelihood-based. We consider typical GLM cases where means are either real-valued, constrained to be positive, or constrained to be on the unit interval. The resulting model is applied to two example datasets through Bayesian analysis. Supporting the extra variation is seen to improve residual plots and produce widened prediction intervals reflecting the uncertainty. Supplementary materials for this article are available online.     

ESTIMATING A STOCHASTIC MODEL OF POPULATION DYNAMICS WITH AN APPLICATION TO KANGAROOS

In this study, we derive stochastic models of population dynamics and devise a new method of estimating the models. The models allow growth and harvest to be nonlinear functions of stochastic processes and the error terms to be nonlinear and heteroskedastic. Ordinary least-squares estimates would be biased and inefficient and generalized least-squares estimates cannot be calculated. Therefore, we implement nonlinear maximum likelihood methods to find unbiased and efficient estimates of parameters. The method is applied to the population dynamics of kangaroos in South Australia. Aerial survey data of kangaroo numbers are combined with harvest, effort and rainfall data to estimate the growth and harvest functions and the variances of the stochastic processes which drive the system. Results suggest that growth and harvest should be modeled as functions of stochastic processes and that observations on kangaroo numbers are critical for estimating population dynamics. The results also indicate that the estimation method works well and is a viable alternative to ARIMA and GARCH models, particularly for small data sets.     

Large sample prediction intervals for future geometric mean a comparative study

This paper provides simulation comparisons among the performance of 11 possible prediction intervals for the geometric.mean of a Pareto distribution with parameters (αB, ). Six different procedures were used to obtain these intervals , namely; true inter -val , pivotal interval , maximum likelihood estimation interval, centrallimit teorem interval, variance stabilizing interval and a mixture of the above intervals . Some of these intervals are valid if the observed sample size m,are large , others are valid if both, n and the future sample size m, are large. Some of these intervals require a knowledge of α or B, while others do not. The simulation validation and efficiency study shows that intervals depending on the MLE's are the best. The second best intervalsare those obtained through pivotal methods or variance stabilization transformation. The third group of intervals is that which depends on the central limit theorem when λ is known. There are two intervals which proved to be unacceptable under any criterion.     

���ɾʧ�����»��ָ���ֲ��Ĺ���

The hybrid censoring scheme is a mixture of type-I and type-II censoring schemes. It is a popular censoring scheme in the literature of life data analysis. Mixed exponential distribution (MED) models is a class of favorable models in reliability statistics. Nevertheless, there is no much discussion to focus on parameters estimation for MED models with hybrid censored samples. We will address this problem in this paper. The EM (Expectation-Maximization) algorithm is employed to derive the closed form of the maximum likelihood estimators (MLEs). Finally, Monte Carlo simulations and a real-world data analysis are conducted to illustrate the proposed method.     

Stochastic comparisons of multivariate mixture models

In this paper we consider sufficient conditions in order to stochastically compare random vectors of multivariate mixture models. In particular we consider stochastic and convex orders, the likelihood ratio order, and the hazard rate and mean residual life dynamic orders. Applications to proportional hazard models and mixture models in risk theory are also given.     

Maximum Kernel Likelihood Estimation

We introduce an estimator for the population mean based on maximizing likelihoods formed by parameterizing a kernel density estimate. Due to these origins, we have dubbed the estimator the maximum kernel likelihood estimate (MKLE). A speedy computational method to compute the MKLE based on binning is implemented in a simulation study which shows that the MKLE at an optimal bandwidth is decidedly superior in terms of efficiency to the sample mean and other measures of location for heavy tailed symmetric distributions. An empirical rule and a computational method to estimate this optimal bandwidth are developed and used to construct bootstrap confidence intervals for the population mean. We show that the intervals have approximately nominal coverage and have significantly smaller average width than the standard t and z intervals. Finally, we develop some mathematical properties for a very close approximation to the MKLE called the kernel mean. In particular, we demonstrate that the kernel mean is indeed unbiased for the population mean for symmetric distributions.     

线性混合模型中方差分量的估计与QR分解

在线性混合模型中, 极大似然估计是一种很重要的估计方法, 但是它常常需要通过迭代求解. 应用设计阵的QR分解, 可以把设计阵变换成上三角矩阵. 这样可以降低参与迭代运算的矩阵的阶数, 还可以减少参与运算的数据量, 从而提高运算的速度. 本文讨论了QR分解在EM算法中的应用, 并用模拟的方法验证了QR分解可以极大的提高运算的速度. 本文同时讨论了QR分解在另外一种估计方法, 即ANOVA估计中的应用.     

roperties and Applications of Alpha Power Gamma Distribution

In this paper, the gamma distribution has been extended by adding an extra shape parameter, we refer to the new distribution as alpha power gamma distribution. It is found that the distribution has a relatively flexible hazard rate function. The properties of the new distribution are studied, including explicit expressions for the $s^{\text{th}}$ raw moments, moment generating function and distributions of order statistics are derived. Also, the integral expressions for the entropy, mean residual life and mean waiting time are obtained. The maximum likelihood estimators of the distribution parameters under complete sample are discussed, the Fisher information matrix is derived. Then, the estimation of the parameters under the general progressive type-II censoring is studied. Finally, the real data set is used to illustrate the practicality of the proposed distribution.