纵向数据下半参数混合效应模型的估计

考虑纵向数据下一类半参数混合效应模型.应用核权函数法以及矩估计法给出了总体效应和个体效应的估计.在一般的条件下,证明了总体效应估计的渐近正态性,并给出该估计的置信区域.对总体效应和个体效应的估计进行了模拟研究,模拟显示估计效果较好.     

随机设计非线性混合模型的统计分析

本文研究了个体观察次数为随机的非线性 混合效应模型中参数的点估计以及区间估计. 在仅给出适当的矩条件下, 给出了固定效应、随机效应的方差阵以及误差方差的矩估计, 并证明了估计量的相合性及渐近正态性. 为给出误差方差以及随机效应方差分量的置信区间, 本文也给出了误差及随机效应的四阶矩估计. 随机模拟说明了方法的有效性.     

线性混合效应模型的正交经验似然推断

基于经验似然方法和QR分解技术, 对线性混合效应模型提出了一个基于正交经验似然的估计方法. 在一些正则条件下, 证明了所提出的经验对数似然比函数渐近服从卡方分布, 进而给出了模型固定效应的置信区间估计. 所提出估计过程不受模型随机效应的影响, 进而保证了所给出的估计是比较有效的. 一些数值模拟和实例分析进一步表明了所提出的估计方法是行之有效的.     

半参数混合效应模型中的估计及其强相合性

将Tao等(1999)提出的线性混合效应模型推广为半参数混合效应模型,给出了模型参数、回归函数和随机效应密度的估计,并研究了估计的强相合性及部分强相合速度.统计模拟表明我们给出的估计方法是可行的.     

偏正态混合效应模型参数的经验贝叶斯估计

针对偏正态混合效应模型,研究模型固定效应和偏度参数的经验贝叶斯估计问题.首先,基于固定效应和偏度参数的先验分布及贝叶斯法则,给出其后验分布.进而,综合运用极大似然估计方法和MCMC技术,获得固定效应和偏度参数的经验贝叶斯估计及其算法.模拟结果表明,在均方误差意义下,经验贝叶斯估计在大部分情况下优于由Nelder-Mead算法获得的极大似然估计.最后,将经验贝叶斯估计应用于中国长三角城市群人口增长的影响因素分析.     

方差分量线性模型中回归系数和参数的所有可容许线性估计

对固定效应方差分量模型，在矩阵损失（ｄ－Ｓ＿τ）（ｄ－Ｓ＿τ）＇下，我们给出了线性可估函数Ｓτ的线性估计在一切估计类中可容许的充要条件；对具有两个方差分量的随机效应线性模型在矩阵损失（ｄ－Ｓα－Ｑβ）（ｄ－Ｓα－Ｑβ）＇下，我们给出了线性可估函数Ｓα＋Ｑβ的线性估计在一切估计类中可容许的充要条件。     

混合线性模型效应参数的影响分析

该文考虑非平衡混合线性模型的影响分析及强影响点的探测问题．文中导出了在单点剔除模型下效应参数的经验Ｂａｙｅｓ估计与原模型下对应估计的相互关系．利用Ｃｏｏｋ距离和协方差比统计量，我们分别给出了剔除单个数据点对固定效应和随机效应参数估计以及估计精度的影响度量．最后，给出具体的计算方法，并对一实例进行分析．     

面板数据下带固定效应的线性回归模型的稳健变量选择

本文结合复合分位数回归和自适应LASSO惩罚方法为固定效应面板数据模型提供了一种稳健变量选择过程。先通过正向正交偏差变换消除固定效应,再利用自适应LASSO构造惩罚复合分位数回归目标函数,进而同时进行回归系数的估计和变量选择。在一些正则条件下,证明了所提出的估计具有Orcale性质。该方法不仅消除了固定效应对估计的影响,而且具有稳健性。模拟研究了所提出方法的有限样本性质并将其应用于实际数据分析。     

缺失数据下线性模型回归系数估计的大样本性质

在响应变量满足MAR缺失机制下，我们分别研究了基于观察到的完全样本数据对、基于固定补足后的“完全洋本”和基于分数线性回归填补后的“完全洋本”得到的回归系数的最小二乘估计的弱相合性、强相合性及渐近正态性，我们还通过数值模拟，比较了基于上述估计得到的β的置信区间的优劣。     

缺失数据下线性EV模型的参数估计

给出EV模型下数据具有随机缺失时,模型参数的一种估计方法,并以一个简单模型为例给出了这种新估计的渐近正态性的具体结果.模拟研究表明,即使在有限样本情形,提出的方法在估计效率上也具有一定优势.     

Estimation of covariance matrices in fixed and mixed effects linear models

The estimation of the covariance matrix or the multivariate components of variance is considered in the multivariate linear regression models with effects being fixed or random. In this paper, we propose a new method to show that usual unbiased estimators are improved on by the truncated estimators. The method is based on the Stein–Haff identity, namely the integration by parts in the Wishart distribution, and it allows us to handle the general types of scale-equivariant estimators as well as the general fixed or mixed effects linear models.     

Digital modeling and control of multiple time-delayed distributed power grid

Distributed power grid (DPG) control systems are so highly interconnected that the effects of local disturbances as well as transmission time delays can be amplified as they propagate through a complex network of transmission lines. These effects deteriorate control performance and could possibly destabilize the overall system. In this paper, a new approximated discretization method and digital design for DPG control systems with multiple state, input and output delays as well as a generalized bilinear transformation method are presented. Based on a procedure for the generation of impulse response data, the multiple fractional/integer time-delayed continuous-time system is transformed to a discrete-time model with multiple integer time delays. To implement the digital modeling, the singular value decomposition (SVD) of a Hankel matrix together with an energy loss level is employed to obtain an extended discrete-time state space model. Then, the extended discrete-time state space model of the DPG control system is reformulated as an integer time-delayed discrete-time system by computing its observable canonical form. The proposed method can closely approximate the step response of the original continuous time-delayed DPG control system by choosing various energy loss levels. For completeness, an optimal digital controller design for the DPG control system and a generalized bilinear transformation method with a tunable parameter are also provided, which can re-transform the integer time-delayed discrete-time model to its continuous-time model. Illustrative examples are given to demonstrate the effectiveness of the developed method.     

Stochastic production frontiers and panel data: A latent variable framework

This paper deals with the issue of estimating production frontier and measuring efficiency from a panel data set. First, it proposes an alternate method for the estimation of a production frontier on a short panel data set. The method is based on the so-called mean-and-covariance structure analysis which is closely related to the generalized method of moments. One advantage of the method is that it allows us to investigate the presence of correlations between individual effects and exogenous variables without the requirement of some available instruments uncorrelated with the individual effects as in instrumental variable estimation. Another advantage is that the method is well suited to a panel data set with a short number of periods. Second, the paper considers the question of recovering individual efficiency levels from the estimates obtained from the mean-and-covariance structure analysis. Since individual effects are here viewed as latent variables, they can be estimated as factor scores, i.e., weighted sums of the observed variables. We illustrate the proposed methods with the estimation of a stochastic production frontier on a short panel data of French fruit growers.     

Mixed effects regression trees for clustered data

This paper presents an extension of the standard regression tree method to clustered data. Previous works extending tree methods to accommodate correlated data are mainly based on the multivariate repeated-measures approach. We propose a “mixed effects regression tree” method where the correlated observations are viewed as nested within clusters rather than as vectors of multivariate repeated responses. The proposed method can handle unbalanced clusters, allows observations within clusters to be split, and can incorporate random effects and observation-level covariates. We implemented the proposed method using a standard tree algorithm within the framework of the expectation-maximization (EM) algorithm. The simulation results show that the proposed regression tree method provides substantial improvements over standard trees when the random effects are non negligible. A real data example is used to illustrate the method.     

Frequency analysis of rotating truncated conical shells using the Haar wavelet method

In this study, we present an analysis of the frequency characteristics of rotating truncated conical shells using the Haar wavelet method. Based on the Love first-approximation theory, the governing equations are formulated by considering the effects of centrifugal and Coriolis forces as well as the initial hoop tension due to rotation. The displacement field is expressed as the Haar wavelet series in the axial direction and trigonometric functions in the circumferential direction. By considering the boundary conditions, the eigenvalue equation is obtained to determine the vibration behaviors of rotating conical shells. To validate the current analysis, the results obtained by the proposed method are compared with those reported previously, where the agreement is very good. Finally, we investigate the effects of the geometrical parameters, rotation speed, and boundary conditions on the vibration characteristics of rotating conical shells and the results are presented.     

Wave induced vibrations of gravity platforms: a stochastic theory

This paper presents a consistent stochastic method to evaluate wave induced vibrations of offshore platforms with special emphasis on gravity type structures. The wavy sea surface is idealized as a stationary and homogeneous stochastic Gaussian (or semi-Gaussian) field. The wave loading processes are treated by applying the concepts of probabilistic potential theory and the stochastic linearization method. The structure is modelled according to the finite element method using boundary spring-dashpot elements to idealize the soil-foundation system. The linearized equations of motion are solved by the frequency response method accounting properly for the temporal and spatial structure of waves as well as for time dependent system function. Numerical results for a 170m high concrete platform are presented including a parametric study of effects due to the shape of the wave spectral density.     

Use of the Probability Integral Transformation to Fit Nonlinear Mixed-Effects Models With Nonnormal Random Effects

This article describes a simple computational method for obtaining the maximum likelihood estimates (MLE) in nonlinear mixed-effects models when the random effects are assumed to have a nonnormal distribution. Many computer programs for fitting nonlinear mixed-effects models, such as PROC NLMIXED in SAS, require that the random effects have a normal distribution. However, there is often interest in either fitting models with nonnormal random effects or assessing the sensitivity of inferences to departures from the normality assumption for the random effects. When the random effects are assumed to have a nonnormal distribution, we show how the probability integral transform can be used, in conjunction with standard statistical software for fitting nonlinear mixed-effects models (e.g., PROC NLMIXED in SAS), to obtain the MLEs. Specifically, the probability integral transform is used to transform a normal random effect to a nonnormal random effect. The method is illustrated using a gamma frailty model for clustered survival data and a beta-binomial model for clustered binary data. Finally, the results of a simulation study, examining the impact of misspecification of the distribution of the random effects, are presented.     

A unified method and its application to brake instability analysis involving different types of epistemic uncertainties

The key idea of the proposed method is the use of the equivalent variables named as evidence-based fuzzy variables, which are special evidence variables with fuzzy focal elements. On the basis of the equivalent variables, an uncertainty quantification model is established, in which the unified probabilistic information related to the uncertain responses of engineering systems can be computed with the aid of the fuzziness discretization and reconstruction, the belief and plausibility measures analysis, and the interval response analysis. Monte Carlo simulation is presented as a reference method to validate the accuracy of the proposed method. The proposed method then is extended to perform squeal instability analysis involving different types of epistemic uncertainties. To illustrate the feasibility and effectiveness of the proposed method, seven numerical examples of disc brake instability analysis involving different epistemic uncertainties are provided and analyzed. By conducting appropriate comparisons with reference results, the high accuracy and efficiency of the proposed method on quantifying the effects of different epistemic uncertainties on brake instability are demonstrated.     

Two-dimensional inverse heat conduction problem of source strength estimation in cylindrical rods

The radial and circumferential (azimuthal) transient dependence of the strength of a volumetric heat source in a cylindrical rod is estimated with Alifanov's iterative regularization method. This inverse problem is solved as an optimization problem in which a squared residue functional is minimized with the conjugate gradient method. A sensitivity problem is used in the determination of the step size in the direction of descent, while an adjoint problem is solved to determine the gradient. In order to examine the accuracy of estimations, two test cases are considered, one with a radial and timewise dependence and the second with radial, azimuthal as well as timewise dependence. The effects of number of sensors and measurement errors are investigated.     

Solvency supervision based on a total balance sheet approach

In this paper we investigate the adequacy of the own funds a company requires in order to remain healthy and avoid insolvency. Two methods are applied here; the quantile regression method and the method of mixed effects models. Quantile regression is capable of providing a more complete statistical analysis of the stochastic relationship among random variables than least squares estimation. The estimated mixed effects line can be considered as an internal industry equation (norm), which explains a systematic relation between a dependent variable (such as own funds) with independent variables (e.g. financial characteristics, such as assets, provisions, etc.). The above two methods are implemented with two data sets.