Arithmetic returns for investment performance measurement

This paper introduces new money-weighted metrics for investment performance analysis, based on arithmetic means of holding period rates weighted by the investment’s market values. This approach generates rates of return which measure a fund’s or portfolio’s performance and a fund manager’s performance. It also enables to show that the Internal Rate of Return (IRR) is a weighted mean of holding period rates associated with interim values which differ from market values, so that value additivity is violated. The manager’s Arithmetic Internal Rate of Return (AIRR) is shown to be the true period equivalent of the cumulative Time Weighted Rate of Return (TWRR), whereas the period TWRR (a geometric return) provides a different ranking. The method is easily generalized for coping with varying benchmark rates. We also cope with the practical problem of estimating interim values whenever they are not available.     

Maximum integrated likelihood estimator of the interest parameter when the nuisance parameter is location or scale

The problem of estimation of an interest parameter in the presence of a nuisance parameter, which is either location or scale, is studied. Two estimators are considered: the usual maximum likelihood estimator and the estimator based on maximization of the integrated likelihood function. The estimators are compared, asymptotically, with respect to the bias and with respect to the mean squared error. The examples are given.     

Emergence of density dynamics by surface interpolation in elementary cellular automata

A classic problem in elementary cellular automata (ECAs) is the specification of numerical tools to represent and study their dynamical behaviour. Mean field theory and basins of attraction have been commonly used; however, although the first case gives the long term estimation of density, frequently it does not show an adequate approximation for the step-by-step temporal behaviour; mainly for non-trivial behaviour. In the second case, basins of attraction display a complete representation of the evolution of an ECA, but they are limited up to configurations of 32 cells; and for the same ECA, one can obtain tens of basins to analyse. This paper is devoted to represent the dynamics of density in ECAs for hundreds of cells using only two surfaces calculated by the nearest-neighbour interpolation. A diversity of surfaces emerges in this analysis. Consequently, we propose a surface and histogram based classification for periodic, chaotic and complex ECA.     

二维区间密度加权算子及其应用

针对不确定多属性决策中的属性信息分布不均匀,且评价信息多数为二维信息的情况,本文提出了二维区间密度加权算子(TDIDW算子)的属性信息集结方法.依据密度算子的集结过程特点,文章首先定义了二维区间密度加权算子及其合成算子,然后介绍了基于灰色区间聚类法的评价信息分组方法以及基于非线性模型的密度加权向量确定方法,最后进行了算例验证.验证结果表明,该方法可以有效地解决由于属性信息分布不均匀而导致评价结果不准确的问题.     

Ground state solution for a problem with mean curvature operator in Minkowski space

In this paper we prove the existence of a radial ground state solution for a quasilinear problem involving the mean curvature operator in Minkowski space.     

基于主成分—灰色关联度的黑龙江省城镇化水平综合评价

从城市和农村两方面入手,构建了城镇化水平综合评价指标体系.由于主成分分析法和灰色关联分析法各有优缺点,所以这里将主成分分析法和灰色关联分析法进行融合,在规避了两种方法的缺点后,对黑龙江省各市的城镇化水平进行了排序.最后对排序结果进行分析,给出了未来黑龙江省各市城镇化发展方向的一些建议.     

基于证据推理的混合型多指标群组决策方法

针对决策方案的属性值为语言评价等级和区间灰数的灰色多指标群组决策问题,提出一种基于证据推理的灰色多指标群组决策方法.首先,根据语言评价信息的概率分布和效用值等价原理确定定性指标和定量指标的信用结构,进而得到群体等级信用结构决策矩阵,然后,依据证据推理方法,对群组评价信息进行合成,求出各方案在各等级的信任度,最后,利用期望方差排序方法确定整个方案集的排序.具体算例表明方法合理有效.     

基于时间序列与灰色拓扑的春节火灾损失预测

火灾每年给中国带来了巨大的损失,春节期间的火灾损失更是严重.根据1999-2010年春节期间火灾统计资料,火灾四项指标数据具有时序性以及随机波动性、模糊性.运用时间序列与灰色拓扑预测方法相结合预测春节期间火灾发生规律,且预测出未来3年内的火灾发生情况.结果表明,时间序列预测模型的平均绝对误差较小,且所建立的灰色拓扑预测模型的拟合精度都达到"好"的标准.因此,采用时间序列与灰色拓扑预测模型相结合对春节火灾发生情况进行预测,其结果合理可靠,可供理论研究和消防部门做出相应的预防措施参考,以达到有效控制和预防春节火灾的目的.     

西藏林芝地区城镇居民消费支出的G(1,1)模型预测及其影响因素的关联度分析

利用2006—2012年林芝地区城镇居民人均生活消费支出数据为研究对象,应用灰色系统理论建立了林芝地区城镇居民消费的G(1,1)预测模型,对其未来几年的人均生活消费进行预测,分析得出:在未来五年中林芝地区城镇居民人均生活消费支出呈现攀升的态势,平均年增长率预计达到7.93%.并运用灰色关联分析方法对影响林芝地区城镇居民消费支出的主要因素进行系统分析,确定了各因素相对于消费支出的关联程度.