优化高校网络教学资源的对策分析

优化网络教学资源、完善网络教学，是高校扩招后提高本科教学质量的途径之一。为此，高校应根据网络教学的特点，进一步优化网络教学资源：构建具有强交互性、快速搜索等特征的网络课程；在统一的教学服务系统下，编制基于知识点、便于二次开发的素材库；建设教学网站，集成教学资源，实现信息共享。     

基于VaR 的最优资产组合选择策略

基于VaR( Value- at- Risk) 的方法, 对Markowitz 资产组合选择策略作了进一步的研究, 给出了一种选择最优资产组合的新策略, 该策略可以使所选择组合的收益率与风险相匹配, 在一定的置信水平下保证收益率最大而风险最小, 并刻画了投资者对风险的喜好倾向。     

基于委托人-代理人关系的患者就医行为研究

本文通过委托人-代理人关系建立了患者与医疗保险机构之间的博弈模型,并在此基础上求解了给定激励合同下患者的最优努力水平。     

Why is one choice different?

Let X_i be nonnegative independent random variables with finite expectations and . The value is what can be obtained by a “prophet”. A “mortal” on the other hand, may use k1 stopping rules t₁,…,t_k yielding a return E[max_i=1,…,kX_ti]. For nk the optimal return is where the supremum is over all stopping rules which stop by time n. The well known “prophet inequality” states that for all such X_i's and one choice and the constant “2” cannot be improved on for any n2. In contrast we show that for k=2 the best constant d satisfying for all such X_i's depends on n. On the way we obtain constants c_k such that .     

Some Recent Developments in Econometric Inference

Recent results in information theory, see Soofi (1996; 2001) for a review, include derivations of optimal information processing rules, including Bayes' theorem, for learning from data based on minimizing a criterion functional, namely output information minus input information as shown in Zellner (1988; 1991; 1997; 2002). Herein, solution post data densities for parameters are obtained and studied for cases in which the input information is that in (1) a likelihood function and a prior density; (2) only a likelihood function; and (3) neither a prior nor a likelihood function but only input information in the form of post data moments of parameters, as in the Bayesian method of moments approach. Then it is shown how optimal output densities can be employed to obtain predictive densities and optimal, finite sample structural coefficient estimates using three alternative loss functions. Such optimal estimates are compared with usual estimates, e.g., maximum likelihood, two-stage least squares, ordinary least squares, etc. Some Monte Carlo experimental results in the literature are discussed and implications for the future are provided.     

A comparative study of some bias correction techniques for kernel- based density estimators

Methods for obtaining kernel-based density estimators with lower bias and mean integrated squared error than an estimator based on a standard Normal kernel function are described and discussed. Three main approaches are considered which are: firstly by using 'optimal' polynomial kernels as described, for example, by Gasser er a1 (1985); secondly by employing generalised jackknifing as proposed by Jones nd Foster (1993) and thirdly by subtracting an estimator of the principal asymptotic bias term from the original estimator. The emphasis in this initial discussion is on their asymptotic properties. The finite sample performance of those that have the best asymptotic properties are compared with two adaptive estimators, as well as the fixed Normal kernel estimator, in a simulation study.     

Pareto-optimal reinsurance for both the insurer and the reinsurer with general premium principles

Abstract

In this paper, we study Pareto-optimal reinsurance policies from the perspectives of an insurer and a reinsurer, assuming reinsurance premium principles satisfy risk loading and stop-loss ordering preserving. By geometric approach, we determine the forms of the optimal policies among two classes of ceded loss functions, the class of increasing convex ceded loss functions and the class that the constraints on both ceded and retained loss functions are relaxed to increasing functions. Then we demonstrate the applicability of our results by giving the parameters of the optimal ceded loss functions under Dutch premium principle and Wang’s premium principle.     

D-optimal statistical designs with restricted string property

This paper applies Frechet derivatives to derive asymp-totically D-optimal statistical designs where the designmatrix is a (O,l)-matrix having exactly one run [of length at most k(, the number of parameters) of l's in each row. These asymptotic results have been utilized in dealing with the more intractable design problem with a finite number of observations. The problemof E-optimality has also been considered.     

Process improvement by variance reduction for a single filling operation with rectifying inspection

Recently, there has been a great interest in the economics of quality control. Process mean targeting is one of the quality control problems which has attracted many researchers. Many papers have been written on finding the optimal mean setting of the process, but very few papers have considered the value of variance reduction. In this paper, we consider a single filling operation with rectifying inspection. We study the effect of the variance on the process performance. We analyse the cost saving which results from reduction in the process variance. We also provide a numerical example.