动态变系数回归模型的识别与非参数GMM估计

主要研究关于面板数据的有限阶固定效应的动态变系数回归模型(简称FDVCM)的统计推断问题.基于B-样条函数和广义矩估计(简称GMM)方法,首先建立了未知系数函数的非参数GMM估计,并证明大样本情形下该估计达到最优非参数收敛速度且具有渐近正态性质.然而实际问题中模型的动态阶数完全未知,也可能存在其它冗余的回归变量,文中借助文[Fan J,Li R.Variable selection via penalized likelihood and its oracle properties.Journal of the American Statistical Association,2001,96(456):1348-1360]中的smoothly clipped absolute deviation(简称SCAD)惩罚函数同时识别真实的动态阶数和显著的外生回归变量.同时建立了压缩估计的Oracle性质,即所识别的模型与真实模型中的参数估计具有相同的渐近分布.最后,无论是数值试验还是实例数据分析都验证了本文方法的合理性和可行性.     

Weighted Best Local Approximation

In this survey, the notion of a balanced best multipoint local approximation is fully exposed since they were treated in the Lpspaces and recent results in Orlicz spaces. The notion of balanced point, which was introduced by Chui et al. in 1984 are extensively used.     

ASYMPTOTIC BEHAVIOR OF THE ECKHOFF APPROXIMATION IN BIVARIATE CASE

The paper considers the Krylov-Lanczos and the Eckhoff approximations for recovering a bivariate function using limited number of its Fourier coefficients. These approximations are based on certain corrections associated with jumps in the partial derivatives of the approximated function. Approximation of the exact jumps is accomplished by solution of systems of linear equations along the idea of Eckhoff. Asymptotic behaviors of the approximate jumps and the Eckhoff approximation are studied. Exact constants of the asymptotic errors are computed. Numerical experiments validate theoretical investigations.     

Recovery Type a Posteriori Error Estimates of Fully Discrete Finite Element Methods for General Convex Parabolic Optimal Control Problems

This paper is concerned with recovery type a posteriori error estimates of fully discrete finite element approximation for general convex parabolic optimal control problems with pointwise control constraints. The time discretization is based on the backward Euler method. The state and the adjoint state are approximated by piecewise linear functions and the control is approximated by piecewise constant functions. We derive the superconvergence properties of finite element solutions. By using the superconvergence results, we obtain recovery type a posteriori error estimates. Some numerical examples are presented to verify the theoretical results.     

Properties of ε-value functions for a two person differential game

We consider the problem of approximate minimax for the Bolza problem of optimal control. Starting from the method of dynamic programming (Bellman) we define the ?-value function to be the approximation for the value function being a solution to the Hamilton–Jacobi equation.     

A new method to build confidence regions for solutions of stochastic variational inequalities

Stochastic variational inequalities model a large class of equilibrium problems subject to data uncertainty. The true solution to such a problem is usually estimated by a solution to its sample average approximation (SAA) problem. This article proposed a new method to build asymptotically exact confidence regions for the true solution that are computable from the SAA solution.     

Optimization of a highway project planning using a modified genetic algorithm

This paper proposes an optimization method for a national-level highway project planning based on a modified genetic algorithm. The proposed method adds to the existing methods by integrating various planning elements into a single system. A simulation model is used in order to determine the best investment strategy with regard to net present value, time deviation from the initial plan and discrepancy between available resources and investment costs by taking into account economical, social, traffic and political factors. The outcome is a project schedule with an optimized cash flow. The proposed method was tested using the example of the National Highway Programme in Slovenia.     

A simple but NP-hard problem of mixed-discrete programming and its solution by approximate algorithms

A NP-hard problem (P) of mixed-discrete linear programming is considered which consists in the minimization of a linear objective function subject to a special non-connected subset of an unbounded polymatroid. For this problem we describe three polynomial approximate algorithms including a greedy algorithm and a fully polynomial approximation scheme solving a special subproblem of (P).     

计算函数导数的FODF-SPH方法

在光滑粒子流体动力学(Smooth Particle Hydrodynamics:SPH)核近似方法原理的基础上,通过泰勒级数展开提出了计算函数导数的新FODF-SPH(Frist Order Derivative Free:FODF)方法,并分别推导一维、二维及三维情况下,计算函数的导数核估计的离散形式.用不同的粒子间距和不同的光滑长度计算一维和二维函数导数,与传统SPH方法进行误差对比分析.结果表明,与传统方法对比提出的计算方法的误差小、收敛速度快且计算过程避免核函数导数计算等优越性,因此在工程应用和数值计算中具有较强的适用范围.