重抽样方法在投资组合理论中的应用与实证分析

在投资组合过程中,由于不了解投资对象的总体分布,可能会过高估计风险回报率.利用重抽样方法可以查看高估程度,采用Shrinkage方法可以改善模型,找到最优的分配权重,帮助投资人确定投资金额分配.基于均值-方差模型与重抽样方法,在不允许卖空的情况下,运用R软件得到了有效的投资组合.     

一种新的梯形模糊数间距离及在投资组合模型选择中的应用

给出一种新的模糊数间的距离公式.用新定义的距离公式来度量给定优先资产的条件下投资组合的分散度.用可能性均值度量投资组合的收益,可能性半方差度量投资组合的风险,在收益和风险满足一定的条件下构造分散度模型.通过实例分析,给出的方法不仅分散度更好,而且资产分配多元化程度更高,计算也更简单.     

投资组合模型

本文建立了考虑交易费用情况下的市场资产组合投资模型,并采用偏好系数加权法对资产的预期收益和总风险进行评价,给出在不同偏好系数下的模型最优解,然后模型讨论了一般情况下的最优投资求解方法,给出定理,在总金额大于某一量值时,可化为线性规划求解。     

不同风险度量约束下带有红利的投资组合模型研究

对现有的在风险度量约束下的投资组合模型进行了推广.建立了带有红利情形的随机股票市场模型,给出了投资组合关于这些风险度量约束下的最优化结果.     

地方总教育投资分配的博弈分析

本文采用博弈论研究地方总教育投资分配的模型 ,该模型包含两个地方政府和一个中央政府 ,并分别为地方政府提供决策 .首先 ,描述了基本模型 ,分别给出了地方政府的效用函数 ;接着分析了地方政府同时行动时的总教育投资分配 ,然后分析了地方政府顺序行动时的总教育投资分配 ;最后给出了最优解的算法并举例说明地方政府怎样去做决策     

基于模糊收益率的最优投资组合模型

考虑了收益率为模糊数的投资组合问题.在一定置信水平上,用收益率波动差的平方和作为风险的度量,在预期收益率给定时,建立了风险最小化的投资组合模型.投资者可以参考其最优解来减小投资风险.最后给出了一个实例.     

考虑Vasicek利率和相依风险的最优投资与再保险

本文研究了利率由Vasicek过程描述,两类保险业务具有相依风险的最优投资和再保险模型.盈余过程由扩散近似模型刻画,保险人的目标是在给定期望终端财富的情况下,寻找使得终端财富的方差最小的投资和再保险策略.通过使用随机线性二次最优控制理论,建立Hamilton-Jacobi-Bellman(HJB)方程,我们获得了值函数的精确表达式以及最优投资和再保险策略.另外,我们给出了有效策略和有效前沿.最后,通过数值例子说明了模型参数对最优投资和再保险策略的影响.     

不确定市场条件下的稳健最优投资组合

本文假设风险资产和无风险资产收益的相关参数属于某个已知的凸多面体,分别讨论了在市场不存在无风险资产和存在无风险资产的情况下稳健最优投资组合问题,给出了问题的解析解,从而推广了Markowitz均值-方差模型的结果.     

保险公司的最优投资策略选择

保险公司传统的投资模型只允许保险公司在保费收取与赔付之间的时滞范围内投资,即投资期间不收取保费也不允许任何赔付发生。本文研究的模型克服了传统模型的不足,投资期间可以收取保费也可以接受索赔。模型在保证保险公司实现目标收益的条件下,使得公司面临的风险最小。另外在模型中引进一个安全投资比例,即保险公司以此比例的财富用于风险投资是相对安全的。通过求解模型,得到保险公司的最优投资策略和风险最小情况下用于投资的财富的比率,并讨论了保费、索赔对投资的影响;另外还得到保险公司投资组合的有效边界,并讨论了有效边界的动态性质;最后用实际数据对保险公司如何选择安全投资比例、如何分配投资资金进行了模拟。     

一种市场风险条件的贷款组合优化决策模型

针对不确定投资情况下风险与收益的选择方法，提出一种贷款组合的优化决策模型，以解决不同风险，收益下的贷款组合决策问题，并给出实例分析以表明该模型的科学性。     

Ruin theory for classical risk process that is perturbed by diffusion with risky investments

In this paper, we study the ruin theory for classical risk process that is perturbed by diffusion with risky investments. We obtain the upper bound for the minimal ruin probability. We also investigate the relationships between the adjustment coefficient and the diffusion volatility parameter, the risk‐free rate and the correlation coefficient by numerical calculation. We give the relationships between ruin and investment. Copyright © 2008 John Wiley & Sons, Ltd.     

保险人投资策略与破产的关系

本文主要考虑带投资收益的风险模型,在该模型下保险人可以根据盈余投资,投资的数量为时间t的函数,我们得到保险人投资策略与破产概率与t时刻所满足的积分-微分方程.     

Annual intrinsic value of a company in a competitive insurance market

In this paper we analyze a measure of the insurance company’s value in an extended Lundberg model which includes the effect of competition on pricing. The extended model is designed to be an integral part of a multi-year controlled risk model of a company operating on both competitive insurance and financial markets, when insureds migrate in seeking for better rates and investors migrate in seeking for higher return on investments.     

Distributions for the risk process with a stochastic return on investments

In this paper, we consider a risk model with stochastic return on investments. We mainly discuss the ruin probability, the surplus distribution at the time of ruin and the supremum distribution of the surplus before ruin. We prove some properties for these distributions and derive the integro-differential equations satisfied by them. We present the relation between the ruin probability and the supremum distribution before ruin.     

养老保险基金投资的目标规划模型

本文根据养老保险基金的性质和投资运营的基本原则,利用单指数模型衡量投资组合的收益和风险,建立了养老保险基金投资的目标规划模型。     

Optimal Investment and Dividend Strategy in the Discrete Sparre Andersen Risk Model

In the discrete-time Sparre Andersen risk model with investments and dividend payments, the company controls the dividend payments and the proportions of venture investments in order to maximize the cumulative expected discounted dividends prior to ruin. The paper gets the algorithm of the optimal dividend strategy by analyzing a Hamilton-Jacobi-Bellman equation and transforming the value function. Furthermore, the existence of the optimal solution of the transformation function is proved by using compression mapping and fixed point principle. In order to make the calculation easier, this paper also proposes an innovative random simulation method for the optimal strategy, and proves that the simulation result is the consistent estimate of the real value. Finally, the random simulation method in the Matlab is used for numerical analysis in an example, which shows the innovative simulation method is a very good and helpful method for making dividend payment and investment decisions.     

On optimal control of capital injections by reinsurance and investments

This is a review paper on the optimal control of capital injections by reinsurance and investments. We will focus on the two most popular models for the surplus process of an insurer: a classical risk model and its diffusion approximation. Both models are modified by the possibility of reinsurance and investments into a risky or riskless asset. The insurer is allowed to change the amount to be invested and the retention level of the reinsurance continuously, i.e. we consider dynamic reinsurance and investment strategies. In addition, the cedent has to inject capital in order to keep the surplus positive. As a risk measure we choose the value of the expected discounted capital injections. The problem is to minimize the expected discounted capital injections over all admissible reinsurance and investments strategies and to find the optimal strategy if it exists. A detailed discussion of the topic can be found in my doctoral thesis “Optimal Control of Capital Injections by Reinsurance and Investments” (Eisenberg in Optimal control of capital injections by reinsurance and investments. PhD thesis, Universität zu Köln, 2010), which is the Gauss prize winning paper of 2009.     

多对模糊算子的综合评判模型

本文提出了一个用多对模糊算子进行模糊综合评判的新模型．用此模型对多个评判对象的几种指标进行评判和排序．     

A Diffusion Perturbed Risk Process with Stochastic Return on Investments

Abstract

A general risk model that allows for stochastic return on investments as well as perturbation by diffusion is studied. Integro-differential equations for the distributions of the time of ruin, the surplus prior to ruin and the deficit at ruin of this model are established. In particular, we consider a diffusion perturbed risk model with interest force in details.     

Optimal investment policy of an insurance firm

In this paper we consider an investment problem by an insurance firm. As in the classical model of collective risk, it is assumed that premium payments are received deterministically from policyholders at a constant rate, while the claim process is determined by a compound Poisson process. We introduce a conversion mechanism of funds from cash into investments and vice versa. Contrary to the conventional collective risk model we do not assume a ruin barrier. Instead we introduce conversion costs to account for the problems implicit in reaching the zero boundary. The objective of the firm is to maximize its net profit by selecting an appropriate investment strategy. A diffusion approximation is suggested in order to obtain tractable results for a general claim size distribution.