Unified Variable Selection for Varying Coefficient Models with Longitudinal Data

Variable selection for varying coefficient models includes the separation of varying and constant effects, and the selection of variables with nonzero varying effects and those with nonzero constant effects. This paper proposes a unified variable selection approach called the double-penalized quadratic inference functions method for varying coefficient models of longitudinal data. The proposed method can not only separate varying coefficients and constant coefficients, but also estimate and sele...     

A New Statistic for Variable Selection in Questionnaire Analysis

1　 IntroductionIn questionnaire analysis,there are two important problems.One is called variableselection or assessment of question worth by which we mean a questionnaire that shouldconsist of those questions which are helpful to distinguish the respondents,in anotherword,a question should be discarded if it doesn′t offer sufficient information fordistinguishing the groups.The other is the problem of discriminant analysis,that is,anew respondent should be properly put into a certain group ba…     

相关MIMO信道下可变数目天线选择算法

提出两种多入多出（MIMO）系统可变数目天线选择算法,来动态适应多种相关MIMO信道环境。基于特征值准则的算法按照最小特征值与特征值总和之比动态选择天线,避免天线间的高度相关性;基于容量准则的算法在保证容量接近最大值的条件下,最小化天线数目。仿真结果表明,两种算法在天线选择后的容量均接近选择前的情况;通过结合链路自适应技术,可进一步得到优于无天线选择系统的数据速率和误码性能。     

Local Linear Estimation by TSLS with Variable Bandwidth for Semi-parametric Simultaneous Equation Models in Econometrics

Econometric simultaneous equation models play an important role in making economic policies, analyzing economic structure and economic forecasting. This paper presents local linear estimators by TSLS with variable bandwidth for every structural equation in semi-parametric simultaneous equation models in econometrics. The properties under large sample size were studied by using the asymptotic theory when all variables were random. The results show that the estimators of the parameters have consistency and asymptotic normality, and their convergence rates are equal to n^-1/2. And the estimator of the nonparametric function has the consistency and asymptotic normality in interior points and its rate of convergence is equal to the optimal convergence rate of the nonparametric function estimation.     

Variable Selection of Varying Dispersion Student-t Regression Models

The Student-t regression model is a useful extension of the normal model,which can be used for statistical modeling of data sets involving errors with heavy tails and/or outliers and provides robust estimation of means and regression coefficients.In this paper,the varying dispersion Student-t regression model is discussed,in which both the mean and the dispersion depend upon explanatory variables.The problem of interest is simultaneously select significant variables both in mean and dispersion model.A unified procedure which can simultaneously select significant variable is given.With appropriate selection of the tuning parameters,the consistency and the oracle property of the regularized estimators are established.Both the simulation study and two real data examples are used to illustrate the proposed methodologies.     

灰色关联度分析在变量筛选应用中的误区

探讨了多元回归建模中灰色关联度分析应用于变量筛选时存在的问题及其原因 ;结合实例阐明 ,GM(1 ,n )模型本身无法克服模型的多重相关性 ,用灰色关联度分析来筛选变量所获得的 GM(1 ,n )模型是不可靠的.     

Variable Selection via Generalized SELO-Penalized Cox Regression Models

The seamless-L_0(SELO) penalty is a smooth function that very closely resembles the L_0 penalty, which has been demonstrated theoretically and practically to be effective in nonconvex penalization for variable selection. In this paper, the authors first generalize the SELO penalty to a class of penalties retaining good features of SELO, and then develop variable selection and parameter estimation in Cox models using the proposed generalized SELO(GSELO) penalized log partial likelihood(PPL) approach. The authors show that the GSELO-PPL procedure possesses the oracle property with a diverging number of predictors under certain mild, interpretable regularity conditions. The entire path of GSELO-PPL estimates can be efficiently computed through a smoothing quasi-Newton(SQN) with continuation algorithm. The authors propose a consistent modified BIC(MBIC) tuning parameter selector for GSELO-PPL, and show that under some regularity conditions, the GSELOPPL-MBIC procedure consistently identifies the true model. Simulation studies and real data analysis are conducted to evaluate the finite sample performance of the proposed method.     

基于主基底分析的两阶段变量筛选方法

在实际系统分析及建模中,人们往往需要保留一些特别重要的分析变量。本文改进了基于主基底的变量筛选方法,分两个阶段来筛选系统分析所需变量。用重要变量构建初始主基底超平面,作为筛选其他普通变量的起点。该方法既结合了人们的定性分析经验,又保留了基于主基底分析的变量筛选方法能够自动筛选系统分析所需最简变量集合的特点,达到了数据降维目的。实际案例分析验证了该方法的有效性。     

基于Jeffreys非信息超先验的贝叶斯变量选择算法

在计算机试验中,复杂现象的仿真拥有数目庞大的输入变量,因此,筛选出对输出影响重要的输入变量是至关重要的。我们通过Jeffreys非信息超先验,提出了一种新的贝叶斯变量选择算法。不同于计算机试验中存在的变量选择算法,我们的方法不需要调节控制稀疏性的超参数。新的变量选择方法通过EM（expectation-maximization）算法求解,试验结果表明,我们的方法不仅取得了理想的效果,而且大大地减少了计算的负担。     

基于SEM的生产性服务质量关键影响因素

随着制造业服务化趋势的日渐显现,生产性服务质量问题已成为学术与企业界关注的焦点.对生产性服务质量的关键影响因素进行了研究.在SERVPREF量表的基础上,构建了包含5个潜变量的服务质量模型,分别为:有形性、可靠性、响应性、保证性和移情性.通过问卷调查获取研究数据,运用SEM完成了信度及模型适配度分析,最终得到了影响服务质量的关键因素及各因素之间的相关性.     

变饱和状态柔性变结构控制系统设计

为了缩短控制系统的调节和整理时间,提出了变饱和状态柔性变结构控制系统设计方法。该方法在系统存在较大偏差时只通过线性控制器调节,在中等偏差时通过线性控制器和变饱和状态控制器一起调节,在小偏差时由线性控制器和由变饱和状态控制器转变的线性控制器一起调节,从而提高了对控制约束的利用。仿真结果表明:该方法在调节和整理时间以及跟踪精度上均优于滑模控制,而且控制信号平滑。     

供应链合作伙伴选择的层次变权多因素决策

针对企业在选择供应链合作伙伴时,常权综合方法难以体现决策者对决策因素的均衡性要求和激励性要求,以及常权综合方法常常违背决策因素间不可替代性的弊病,提出了一种基于可拓理论和变权理论的新方法———层次变权优度评价法.该方法克服了常权综合的弊病,能够对某些重要影响因素进行均衡性处理的同时,对某些关键影响因素进行激励,从而使决策者意愿的体现建立在科学理论的基础之上.经实证研究,证实了该方法应用的灵活性和有效性.     

基于SEM的工程项目知识获取能力相关性分析与检验

在知识经济时代,组织的知识获取能力是生存发展的基础。为适应市场变化和激烈竞争,工程项目管理中必须清楚其知识管理现状,进而提升其知识管理能力,这需要一套完整的、适合工程项目特点的知识管理理论和方法。本文界定了工程项目知识管理的内涵,提出知识管理能力的7个构成要素,构建了模型及研究假设,设计了各要素能力的度量量表。通过问卷调查获取了研究数据资料,对量表进行信度、效度检验,并由此构建了各要素能力的度量指标体系。通过结构方程对概念模型进行了检验,从而明确了知识获取能力的相关性要素和影响程度。     

基于个体选择的小世界网络结构演化

将复杂网络理论和基于博弈论的经济网络理论相结合，探讨小世界网络的结构演化问题。从个体选择的角度，以网络中个体价值优化作为网络结构演化的动力机制，用顶点度分布(P(K))、平均最短路径长度(l)、集群系数(C)作为网络结构演化判据，研究小世界网络的结构演化问题。     

Quasi-Stepwise Regression Variable Selection and its Application in Rural Household Net Income Forecasting

Quasi-Stepwise regression variable selection method based on validation of least absolute deviation regression is proposed. The method shows good performance in its application to rural household net income forecasting. Three models with high accuracy are constructed based on this method. According to these models, factors affecting rural household net income are analyzed, and some policy suggestions are given to increase the rural household net income.     

灰色模型GM(1,n)的变量选择及拟合度分析

根据灰色关联度,探讨了ＧＭ（１, ｎ ）拟合度与变量选择的关系．应用实例,说明了变量选择在灰色建模过程中的必要性．     

Matching Algorithms of Minimum Input Selection for Structural Controllability Based on Semi-Tensor Product of Matrices

In 2011, Liu, et al. investigated the structural controllability of directed networks. They proved that the minimum number of input signals, driver nodes, can be determined by seeking a maximum matching in the directed network. Thus, the algorithm for seeking a maximum matching is the key to solving the structural controllability problem of directed networks. In this study, the authors provide algebraic expressions for matchings and maximum matchings proposed by Liu, et al.(2011)via a new matrix...     

Variable selection for recurrent event data with informative censoring

Recurrent events data with a terminal event(e.g.,death) often arise in clinical and observational studies.Variable selection is an important issue in all regression analysis.In this paper, the authors first propose the estimation methods to select the significant variables,and then prove the asymptotic behavior of the proposed estimator.Furthermore,the authors discuss the computing algorithm to assess the proposed estimator via the linear function approximation and generalized cross validation method for determination of the tuning parameters.Finally,the finite sample estimation for the asymptotical covariance matrix is also proposed.     

Approximate Controllability for Degenerate Heat Equation with Bilinear Control

This paper investigates the nonnegative approximate controllability for the one-dimensional degenerate heat equation governed by bilinear control. Both non-controllability and approximate controllability are studied for the system. If the control is restricted to act on a fixed domain, it is not controllable. If the control is allowed to mobile, it is approximately controllable.     

变参数指数分布先验信息的折合

针对高可靠性复杂系统试验数据少、寿命试验中分布参数变动的特点,讨论了多阶段环境试验下,变参数指数分布先验信息的折合方法。提出了指数分布折合因子的概念,通过该折合因子将不同阶段试验数据折合为现场试验数据,以此作出指数分布中未知参数的折合区间估计和点估计。在寿命分布为指数分布的可靠性增长试验中,在现场样本量较小的情况下,将同分布的历史试验数据进行折合,进而运用Bayes方法评估系统失效率等有重要的意义。最后通过仿真实例验证了该方法的有效性。