Variable selection for generalized varying coefficient partially linear models with diverging number of parameters

Semiparametric models with diverging number of predictors arise in many contemporary scientific areas.Variable selection for these models consists of two components:model selection for non-parametric components and selection of significant variables for the parametric portion.In this paper,we consider a variable selection procedure by combining basis function approximation with SCAD penalty.The proposed procedure simultaneously selects significant variables in the parametric components and the nonparametric components.With appropriate selection of tuning parameters,we establish the consistency and sparseness of this procedure.     

Double penalized variable selection procedure for partially linear models with longitudinal data

Based on the double penalized estimation method,a new variable selection procedure is proposed for partially linear models with longitudinal data.The proposed procedure can avoid the effects of the nonparametric estimator on the variable selection for the parameters components.Under some regularity conditions,the rate of convergence and asymptotic normality of the resulting estimators are established.In addition,to improve efficiency for regression coefficients,the estimation of the working covariance matrix is involved in the proposed iterative algorithm.Some simulation studies are carried out to demonstrate that the proposed method performs well.     

Variable selection for semiparametric varying-coefficient partially linear models with missing response at random

In this paper, we present a variable selection procedure by combining basis function approximations with penalized estimating equations for semiparametric varying-coefficient partially linear models with missing response at random. The proposed procedure simultaneously selects significant variables in parametric components and nonparametric components. With appropriate selection of the tuning parameters, we establish the consistency of the variable selection procedure and the convergence rate of the regularized estimators. A simulation study is undertaken to assess the finite sample performance of the proposed variable selection procedure.     

Model detection and variable selection for varying coefficient models with longitudinal data

In this paper, we consider the problem of variable selection and model detection in varying coefficient models with longitudinal data. We propose a combined penalization procedure to select the significant variables, detect the true structure of the model and estimate the unknown regression coefficients simultaneously. With appropriate selection of the tuning parameters, we show that the proposed procedure is consistent in both variable selection and the separation of varying and constant coefficients, and the penalized estimators have the oracle property. Finite sample performances of the proposed method are illustrated by some simulation studies and the real data analysis.     

Law of iterated logarithm and model selection consistency for generalized linear models with independent and dependent responses

We study the law of the iterated logarithm (LIL) for the maximum likelihood estimation of the parameters (as a convex optimization problem) in the generalized linear models with independent or weakly dependent (\rho-mixing) responses under mild conditions. The LIL is useful to derive the asymptotic bounds for the discrepancy between the empirical process of the log-likelihood function and the true log-likelihood. The strong consistency of some penalized likelihood-based model selection criteria can be shown as an application of the LIL. Under some regularity conditions, the model selection criterion will be helpful to select the simplest correct model almost surely when the penalty term increases with the model dimension, and the penalty term has an order higher than O(log log n) but lower than O(n): Simulation studies are implemented to verify the selection consistency of Bayesian information criterion.     

‘Numerical Linear Algebra with Applications’ impact factor for 2008 has been published to be 0.822

The Journal ‘Numerical Linear Algebra with Applications’ has received its 2008 impact factor. The impact factor for 2008 has been published to be 0.822, an increase from 0.696 in 2007. Copyright © 2009 John Wiley & Sons, Ltd.     

单调缺失机制下高维纵向线性回归模型的变量选择

在响应变量带有单调缺失的情形下考虑高维纵向线性回归模型的变量选择.主要基于逆概率加权广义估计方程提出了一种自动的变量选择方法,该方法不使用现有的惩罚函数,不涉及惩罚函数非凸最优化的问题,并且可以自动地剔除零回归系数,同时得到非零回归系数的估计.在一定正则条件下,证明了该变量选择方法具有Oracle性质.最后,通过模拟研究验证了所提出方法的有限样本性质.     

Sub‐linear capacity scaling for multi‐path channel models

The theoretic capacity of a communication system constituted of several transmitting/receiving elements is determined by the singular values of its transfer matrix. Results based on an independent identically distributed channel model, representing an idealized rich propagation environment, state that the capacity is directly proportional to the number of antennas. Nevertheless there is growing experimental evidence that the capacity gain can be at best scaled at a sub‐linear rate with the system size. In this paper, we show under appropriate assumptions on the transfer matrix of the system that the theoretic information‐capacity of multi‐antenna systems is upper bounded by a sub‐linear function of the number of transmitting/receiving links. Copyright © 2009 John Wiley & Sons, Ltd.     

响应变量存在缺失时部分线性模型的经验似然推断

考虑响应变量带有缺失的部分线性模型,采用借补的思想,研究了参数部分和非参数部分的经验似然推断,证明了所提出的经验对数似然比统计量依分布收敛到χ2分布,由此构造参数部分和函数部分的置信域和逐点置信区间.对参数部分,模拟比较了经验似然与正态逼近方法;对函数部分,模拟了函数的逐点置信区间.     

On martingale diffusions describing the ‘smile‐effect’ for implied volatilities

This paper discusses diffusion models describing the ‘smile‐effect’ of implied volatilities for option prices partly following the new approach of Bruno Dupire. If one restricts to the time homogeneous case, a careful study of this approach shows that the call option prices considered as a function of the price x of the underlying security, remaining time to maturity T–t and strike price K have necessarily to satisfy a certain functional equation, in order to fit into a coherent model. It is shown that for certain examples of empirically observed option prices which are reported in the literature, this functional equation does not hold. © 2000 John Wiley & Sons, Ltd.     

Global well‐posedness for two modified‐Leray‐α‐MHD models with partial viscous terms

In this paper, we will prove global well‐posedness for the Cauchy problems of two modified‐Leray‐α‐MHD models with partial viscous terms. Copyright © 2009 John Wiley & Sons, Ltd.     

Spatial‐skin effect for eigenvibrations of a thick cascade junction with ‘heavy’ concentrated masses

A spectral problem for the Laplace operator in a thick cascade junction with concentrated masses is considered. This cascade junction consists of the junction's body and a great number of ?‐alternating thin rods belonging to two classes. One class consists of rods of finite length, and the second one consists of rods of small length of order . The density of the junction is of order on the rods from the second class and outside of them. The asymptotic behavior of eigenvalues and eigenfunctions of this problem is studied as ? → 0. There exist five qualitatively different cases in the asymptotic behavior of eigenmagnitudes as ? → 0, namely the case of ‘light’ concentrated (α ∈ (0,1)), ‘middle’ concentrated (α = 1), and ‘heavy’ concentrated masses (α ∈ (1, + ∞ )) that we divide into ‘slightly heavy’ concentrated (α ∈ (1,2)), ‘intermediate heavy’ concentrated (α = 2), and ‘very heavy’ concentrated masses (α > 2). In the paper, we study in detail the influence of the concentrated masses on the asymptotic behavior if α ∈ (1,2). We construct the leading terms of asymptotic expansions both for the eigenvalues and eigenfunctions and prove the corresponding asymptotic estimates. Copyright © 2013 John Wiley & Sons, Ltd.     

A multi‐stage ‘infection’ model of stock investors' reaction to new product announcement signal

Drawing on viral dynamics theory, this paper presents a differential equations model with time delay to investigate the stock investor behavior driven by new product announcement (NPA) signal. Visually, we look upon investors in stock market as cells in vivo and the NPA signals as free virus. The potential investors will be ‘infected’ by the dissociative NPA signal and then make investment decisions. In order to better understand the ‘infection’ process, we extract and establish a multi‐stage process during which NPA signal is delivered and ‘infects’ the potential investors. A time‐delay effect is employed to reflect the evaluation stage at which potential investors comprehensively evaluate and decide whether to invest or not. In addition, we introduce a set of external and internal factors into the model, including information sensitivity and investor sentiment, and so on, which are pivotal for examining investor behavior. Equilibrium analysis and numerical simulations are employed to check out the properties of the model and highlight the practical application values of the model. Copyright © 2016 John Wiley & Sons, Ltd.     

‘Modified Hermitian and skew‐Hermitian splitting methods for non‐Hermitian positive‐definite linear systems’ [Numer. Linear Algebra Appl. 14 (2007) 217–235]

In this note, some errors in the article (Numer. Linear Algebra Appl. 2007; 14 :217–235) are pointed out and some correct results are presented. Copyright © 2011 John Wiley & Sons, Ltd.     

Homogenization of eigenvalue problem for Laplace–Beltrami operator on Riemannian manifold with complicated ‘bubble‐like’ microstructure

We study the asymptotic behavior of the eigenvalues and the eigenfunctions of the Laplace–Beltrami operator on a Riemannian manifold M^ε depending on a small parameter ε>0 and whose structure becomes complicated as ε→0. Under a few assumptions on scales of M^ε we obtain the homogenized eigenvalue problem. In addition we study the behavior of the heat equation on M^ε and investigate the large time behavior of the homogenized equation. Copyright © 2009 John Wiley & Sons, Ltd.