再制造成本随机分布和市场细分的生产优化模型

本文研究了单一厂商制造/再制造混合系统的两期生产优化问题。首先,在回收率一定条件下,建立了回收产品的再制造成本与再制造率之间的函数关系;接着,引入消费者偏好系数构造了再制造产品和新制造产品之间的价格竞争和市场细分;然后,建立了以追求利润最大化为目标的模型,证明了该模型为凸规划,给出了K-T条件表达式,并分析了伽马分布条件下解的特征;最后,通过算例对本文模型的性质和规律作进一步分析。     

提前期、构建成本和短缺量拖后率均可控的EOQ模型

传统库存模型通常将提前期和构建成本视为不可控制。事实上可以通过追加投资缩短提前期和降低构建成本。缺货期间,为减少订单丢失量和补偿顾客的损失,供应商会给予一定的价格折扣。现实库存系统中,容易得到需求的期望值和标准差,但较难得到其分布规律。基于此,考虑短缺量拖后率与价格折扣和缺货期间库存水平相关,提出了一种需求为任意分布且提前期和构建成本均可控的EOQ模型,证明了模型存在唯一最优解,给出了一种寻优算法。数值仿真分析表明,一般情况下,压缩提前期和降低构建成本能降低订购批量和安全库存,降低库存总成本;短缺量拖后系数和缺货概率对库存总成本影响较大,企业应尽量降低缺货概率,尤其在短缺量拖后系数较小时。     

收益率分布主观模型及其实证分析

在累积展望理论基础上,通过累积概率描述主观因素对内在价值分布的影响,建立收益率分布主观模型。建立从经验收益率数据中估计投资群体的风险追求程度、投资情绪和非完全理性程度等行为变量参数的方法。利用沪市A股数据,进行χ2同分布拟合检验,结果表明:0.05水平下,沪市69.56%股票的收益率分布认为符合收益率分布主观模型,接受t分布、双正态混合分布、稳定分布和正态分布假设的股票分别为56.31%、44.80%、46.06%和1.74%。通过比较大、小公司投资群体的行为差异,以及利用收益率主观模型估计的内在价值信息参数和行为参数对截面个股收益率进行解释的实证分析,表明收益率分布主观模型及估计行为参数的方法具有合理性。     

The densest <Emphasis Type="Italic">k</Emphasis>-subgraph problem on clique graphs

The Densest k-Subgraph (DkS) problem asks for a k-vertex subgraph of a given graph with the maximum number of edges. The problem is strongly NP-hard, as a generalization of the well known Clique problem and we also know that it does not admit a Polynomial Time Approximation Scheme (PTAS). In this paper we focus on special cases of the problem, with respect to the class of the input graph. Especially, towards the elucidation of the open questions concerning the complexity of the problem for interval graphs as well as its approximability for chordal graphs, we consider graphs having special clique graphs. We present a PTAS for stars of cliques and a dynamic programming algorithm for trees of cliques. M.L. is co-financed within Op. Education by the ESF (European Social Fund) and National Resources. V.Z. is partially supported by the Special Research Grants Account of the University of Athens under Grant 70/4/5821.     

Decision Theory Applied to an Instrumental Variables Model

This paper applies some general concepts in decision theory to a simple instrumental variables model. There are two endogenous variables linked by a single structural equation; k of the exogenous variables are excluded from this structural equation and provide the instrumental variables (IV). The reduced‐form distribution of the endogenous variables conditional on the exogenous variables corresponds to independent draws from a bivariate normal distribution with linear regression functions and a known covariance matrix. A canonical form of the model has parameter vector (ρ, φ, ω), where φis the parameter of interest and is normalized to be a point on the unit circle. The reduced‐form coefficients on the instrumental variables are split into a scalar parameter ρand a parameter vector ω, which is normalized to be a point on the (k−1)‐dimensional unit sphere; ρmeasures the strength of the association between the endogenous variables and the instrumental variables, and ωis a measure of direction. A prior distribution is introduced for the IV model. The parameters φ, ρ, and ωare treated as independent random variables. The distribution for φis uniform on the unit circle; the distribution for ωis uniform on the unit sphere with dimension k‐1. These choices arise from the solution of a minimax problem. The prior for ρis left general. It turns out that given any positive value for ρ, the Bayes estimator of φdoes not depend on ρ; it equals the maximum‐likelihood estimator. This Bayes estimator has constant risk; because it minimizes average risk with respect to a proper prior, it is minimax. The same general concepts are applied to obtain confidence intervals. The prior distribution is used in two ways. The first way is to integrate out the nuisance parameter ωin the IV model. This gives an integrated likelihood function with two scalar parameters, φand ρ. Inverting a likelihood ratio test, based on the integrated likelihood function, provides a confidence interval for φ. This lacks finite sample optimality, but invariance arguments show that the risk function depends only on ρand not on φor ω. The second approach to confidence sets aims for finite sample optimality by setting up a loss function that trades off coverage against the length of the interval. The automatic uniform priors are used for φand ω, but a prior is also needed for the scalar ρ, and no guidance is offered on this choice. The Bayes rule is a highest posterior density set. Invariance arguments show that the risk function depends only on ρand not on φor ω. The optimality result combines average risk and maximum risk. The confidence set minimizes the average—with respect to the prior distribution for ρ—of the maximum risk, where the maximization is with respect to φand ω.     

基于犹豫直觉模糊语言集均值-标准差偏好距离的多属性决策研究

在犹豫直觉模糊语言集和语言尺度函数的基础上定义了均值-标准差偏好的Hamming距离，并提出了基于犹豫直觉模糊语言集距离TOPSIS和TODIM的多属性决策方法，进一步利用这两种方法对实例问题建筑商的招标方案进行排序，并讨论了偏好参数对排序结果的灵敏度分析。为验证上述方法的有效性，与已有方法对同一实例的排序结果进行了比较分析。     

工程质量政府监督多层次利益分配与激励协同机制探究

The implementation of the government supervision of the quality of the project is an international practice. The basic form of government supervision of engineering quality is government supervision on the quality behavior of the engineering main bodies and its results by the competent government department entrusted. Its essence is a dual principal-agent process. The frequent accidents of the engineering quality reflect the loss and failure of the government law enforcement supervision of the engineering quality to some extent. Its root lies in the lack of endogenous power in the law enforcement supervision of the project quality government supervisors in the law enforcement supervision. Therefore, the incentive coordination mechanism of the government supervision based on the multi-level interest distribution is worth explored. In views of the multi-level management system which is formed by the government departments, government quality supervision organizations, quality supervision team (or group) for the government supervision of engineering quality. The benefit distribution function between every party is constructed, and the game model of the multi-level incentive and coordination for the government supervision in engineering quality is built. To solve and deduce from the first stage of the cooperative game and the second stage of the non-cooperative game, the cooperative game can obtain the reward coefficient: . The coordination degree of the best effort can be obtained by the non cooperative game. The result shows that:the coordination degree of government engineering quality supervisor is related to the coordination costs, and had nothing to do with fixed costs. The benefit distribution coefficient not only depends on the efforts of the quality government monitors, but also on the efficiency of other parties' efforts. The quality supervisors of the project will also focus on the coordination with other parties when enhancing their management capabilities to improve the overall performance of project quality government supervision. The strategy of the incentive coordination mechanism for the supervision and cooperation of the project quality government is:the government quality supervision team should set up the supervisory team properly, improve the coordination efficiency and reduce the cost of supervision-coordination to maximize the value of self-motivation. Quality supervision team (or group) should establish the partnership to improve the coordination efficiency for achieving the maximization of their own incentive value.The model and conclusion of incentive synergy mechanism based on multi-level benefit allocation mechanism are researched. It can provide theoretical support and practice reference for the market governance and supervision of general public goods.     

半参数空间ZISF的估计、分类与蒙特卡罗模拟

零无效率随机前沿模型（ZISF）包含随机前沿模型和回归模型,两模型各有一定的发生概率,适用于技术无效生产单元和技术有效生产单元同时存在的情形。本文在ZISF的生产函数中引入空间效应和非参函数,并假设回归模型的发生概率为非参函数,构建了半参数空间ZISF。该模型可有效避免忽略空间效应导致的有偏且不一致估计量,也避免了线性模型的拟合不足。本文对非参函数采用B样条逼近,使用极大似然方法和JLMS法分别估计参数和技术效率。蒙特卡罗结果表明：①本文方法的估计精度和分类精度均较高。随着样本容量的增大,精度增加。②忽略空间效应或者非参数效应,估计精度和分类精度降低,文中模型有存在必要性。③忽略发生概率的非参数效应会严重降低估计和分类精度,远大于忽略生产函数的非参数效应的影响。     

基于共同持有资产的银行间接关联网络研究

金融市场是一个复杂系统,银行之间不仅有直接的拆借关系,还能够通过投资市场建立间接关联。本文分析了资产内生相关性、资产降价出售以及银行投资行为等因素对银行间接关联程度的影响,基于这些因素通过持有共同资产构建银行系统的间接关联,并以此为基础通过平面极大过滤图方法生成银行间接关联网络,论证了该网络中的系统重要性银行,并通过对该网络结构特征的分析,发现间接关联网络具有小世界和无标度等特征,这些特征与银行通过直接拆借形成的网络相似。本文对于银行间接关联网络的研究不仅能够更加清晰地了解银行之间的关系,也为银行系统性风险的监管提供了新的视角。     

续集电影的片名策略及其市场效应研究

以续集电影为研究情境,探讨了电影制作经营方如何通过科学的电影续集片名策略,来提升观众的观影意愿和电影的市场表现.通过两个消费者实验和美国电影市场1960年～2017年的电影数据,研究发现,续集电影采用文字片名策略(vs.数字片名策略)会促使消费者有更高的观影意愿,想象可达性发挥中介作用.但是这一关系受到电影题材的调节,前瞻性题材的续集电影使用文字片名策略会产生更高的观影意愿,而回溯性题材的续集电影使用数字片名策略会产生更高的观影意愿.对影视产业如何采取不同的续集影视片名策略,从而打造影视知名品牌提供了战略启示;为更广泛的文化产业的品牌营销也具有战略借鉴意义.