IMPLICATIONS OF THE UNDERLYING ASSUMPTIONS OF PERT

PERT, as an aid in planning for project managers, has been widely accepted, but as yet there appears to be a wide gap between the user's apparent impression of the underlying assumptions and the theoretical assumptions. This paper points out some of the more common misconceptions and their implications upon the total project. The Beta distribution as the underlying probability distribution is evaluated as to first, the overall effects of the inherent errors that are imposed by the basic PERT assumptions, and second, the effects, from a probability distribution viewpoint, of some of the more common PERT misconceptions. Finally, several alternatives to the basic PERT methodology are explored, both from the theoretical and practical viewpoints.     

On the Generality of the PERT Average Time Formula

It is well known that the PERT average time formula approximation is related to the Beta distribution assumption. In this note, it is shown that if the formula is modified to use the median instead of the mode, then it becomes a good approximation regardless of distribution assumptions. Applications of the formula beyond project management are highlighted.     

PERT,CPM and the export process

PERT techniques logically arrange all related tasks involved in completing a major process. Tasks can be examined in relationship to each other and one can determine whether—and, if so, by how much—changes in the length of time to perform one task affect overall completion time. When applied to the export process, PERT techniques allow one to examine trade-offs between alternatives such as air and water shipping; and to calculate values of accelerating each task.     

A STATISTICAL ANALYSIS OF THE UTILIZATION EFFECTIVENESS OF A PERT PROGRAM

This article is based on the belief that students should learn the computational aspects of decision science techniques outside the classroom, thus freeing the instructor from this task and enabling him to devote more class time to focusing on the theoretical and/or application-oriented elements which will take students further in their learning experience. An experiment was designed to determine the learning value of one way of achieving this, namely the use of a Learning Center where students learned individually using a programmed instruction learning machine. The research involved both graduates and undergraduates learning the fundamentals of PERT—some with the learning machine approach while others were involved in more conventional pedagogies. Surprising success was discovered relative to both the approach and the quality of the PERT program used, with far-reaching implications regarding futuristic approaches to decision science education.     

Subjective estimation bias and PERT statistical procedures

This paper is an evaluation of alternative methods for reducing the impact of systematic bias in subjective estimates for PERT statistical procedures. As such, it represents an application of behavioural research to the improvement of a popular management science tool. The first section defines functions for analyzing the impact of behavioural research on PERT statistical procedures. The manner in which bias patterns impact on expected project costs is discussed. The second section presents several alternative proposals for improving PERT statistical procedures. The third section compares several of the most relevant studies of subjective estimation behaviour and evaluates their implications. Behavioural research in a variety of settings has demonstrated the predominance of a bias pattern that is likely to contribute to cost overruns when the project is expected to be behind schedule and cost penalties when ahead of schedule. The stability of the most common pattern argues for the superiority of including an adjustment constant in PERT statistical procedures as against the use of project monitoring of estimation behaviour.     

基于PERT/CPM的关键链管理

网络规划技术是现代项目管理技术的重要组成部分。本文在对传统PERT/CPM网络规划方法分析的基础上,针对PERT三点估计在应用上的缺陷,引入Theory of Constraint(TOC),并对PERT三点估计给出一种全新的解释。在新的解释下,TOC思想在项目规划中的运用被称为关键链管理(CCPM),强调在项目实施过程中加强对关键链的管理。为此,本文提出了一个基于三点估计的关键链管理的新方法,并通过实例论证关键链管理作为一种新的项目管理方法可以接近或者超过PERT/CPM的平均效果。     

PERT: A DYNAMIC APPROACH

This paper combines learning curves with a PERT network to produce a dynamic PERT model. The dynamic model takes cognizance of the fact that many projects are of a repetitive nature and that the network may vary between runs of the project through the addition or deletion of activities attendant to producing variations of a basic model. Thus, on any given run, the activities comprising a network will exhibit varying degrees of repetitiveness. The proposed model treats the estimated completion times of activities comprising the network as a function of (1) the number of times the various activities have been repeated on prior runs of the project, and (2) the learning rate attendant to each activity. Thus, the estimated completion time for a run through the project changes as additional units are produced. A sixteen event PERT network is simulated (using the proposed dynamic model) through twenty runs of a project. The simulation is conducted under three situations; namely, with learning taking place on (1) only noncritical activities, (2) only critical activities, and (3) all activities. In all three cases the results are compared to the static PERT model. The implications of the proposed model for improved decision making are presented in the concluding remarks of the paper.     

A Cross-Validation Analysis of Neural Network Out-of-Sample Performance in Exchange Rate Forecasting

Econometric methods used in foreign exchange rate forecasting have produced inferior out-of-sample results compared to a random walk model. Applications of neural networks have shown mixed findings. In this paper, we investigate the potentials of neural network models by employing two cross-validation schemes. The effects of different in-sample time periods and sample sizes are examined. Out-of-sample performance evaluated with four criteria across three forecasting horizons shows that neural networks are a more robust forecasting method than the random walk model. Moreover, neural network predictions are quite accurate even when the sample size is relatively small.     

随机订单干扰下考虑合并决策的供应链网络调度研究

为满足客户个性化需求的快速响应，企业需具备柔性的外部供应链网络结构，以协同方式共同完成产品生产。本文考虑具有交互特征的多个不同类型协同供应链网络，构建生产成本、库存成本、等待成本以及订单延期交货成本最小化的目标函数，并设计合并决策判断变量构建同类订单在相同协同企业处的开始时间约束。此外，模型中考虑确定订单以及随机订单两种类型订单，并设计随机订单在区间时间段中离散时间点的到达概率。为获取协同供应链网络生产调度优化策略，基于随机订单到达与否的场景构建四个子决策模型，并进一步设计判断提前安排随机订单协同生产和不提前安排随机订单协同生产不同调度策略下成本差异的主决策模型。仿真结果表明合并决策在带来生产成本效益的同时也引起了部分订单的延期交货，且不同类型的协同供应链网络对随机订单的抗干扰能力存在一定程度的差异。     

信用风险中回收率分布的双Beta模型

本文研究了随机回收率的分布,建立了回收率的双Beta分布密度模型,它具有双峰分布的特点,这与Moody公司的最新研究相吻合,弥补了现有回收率分布模型均为单峰的不足。利用基于数论网格的序贯优化算法对所建模型的参数做出了估计,借助于核密度估计的工具,进行了实证分析,结果表明双Beta模型的拟合误差很小,远小于Beta模型的误差,它是表示回收率理想的模型。最后给出了抽取双Beta分布随机数的方法。     

Heterogeneous dispatching rules in job and flow shops

This paper reports the results of a study of the use of heterogeneous dispatching rules for the scheduling of work in a job shop. The methodology employed included discrete event simulation, using rule combinations determined by prior genetic algorithm searches and generalization using neural networks. Eight dispatching rules were considered, including first in first out (FIFO), earliest due date ( EDD), shortest processing time (SPT), slack/ number of operations (SLK), critical ratio (CR), modified due date (MDD), modified operation due date (MOD), and apparent tardiness cost (ATC). A three-machine job shop was studied, in which three work organizations were employed, pure flow (fixed sequence), pure job shop ( random sequence), and a hybrid shop where flow is random but with unequal probabilities. Three levels of machine loading were used and average tardiness was used as the performance measure. In most cases, modified due date and apparent tardiness cost were the best rules. The application of the best rules effected the results primarily when applied to bottleneck machines or the first machine in a pure flow shop. Nearly any other rule was acceptable on non-botdeneck machines except FIFO and CR, which consistently perform poorly. No major advantage of mixing rules was found.     

A Structural Model of Dense Network Formation

This paper proposes an empirical model of network formation, combining strategic and random networks features. Payoffs depend on direct links, but also link externalities. Players meet sequentially at random, myopically updating their links. Under mild assumptions, the network formation process is a potential game and converges to an exponential random graph model (ERGM), generating directed dense networks. I provide new identification results for ERGMs in large networks: if link externalities are nonnegative, the ERGM is asymptotically indistinguishable from an Erdős–Rényi model with independent links. We can identify the parameters only when at least one of the externalities is negative and sufficiently large. However, the standard estimation methods for ERGMs can have exponentially slow convergence, even when the model has asymptotically independent links. I thus estimate parameters using a Bayesian MCMC method. When the parameters are identifiable, I show evidence that the estimation algorithm converges in almost quadratic time.     

成长性、现有资产与β关系的上市公司实证研究

在资本资产定价模型(CAPM)中,β(系统风险)是决定资产定价的唯一因素。以我国A股上市公司为研究样本,通过将资产风险β分解为成长性风险βG和现有资产风险βA2个部分,探讨了公司的成长性和现有资产对β的影响。研究结果表明,总体上我国证券市场中上市公司的βA显著地大于βA,但不同行业间差异显著。进一步分析显示,若公司规模越大、账面市值比越高、同所处行业的市场竞争程度越低,不仅βG对β的影响更大,而且βG与βA间的差异也越明显。这表明,在我国证券市场中,βG既是β取值大小的重要因素,同时也是风险的主要来源。     

不同态势下β特征及其与收益关系研究

分析了中国证券市场中不同态势下各行业β值的不同表现特征,检验了中国证券市场成立以来至2003年12月13年间β与收益的关系,发现引入市场态势后,条件CAPM的解释能力显著增强;当市场处于牛市(熊市)时,β与收益呈显著正(负)相关;得出了β仍然是度量资产风险的重要方法的结论.     

MODELING TIME-COST TRADE-OFFS IN CPM NETWORKS

A new type of PERT/CPM methodology is introduced whereby the individual activities within a project management network are endowed with resistive and capacitive elements. This methodology will enable us to mathematically define a completion time for the various activities and to relate the completion time to relevant cost in the completion of a particular task. It will also allow us to define the work done, and the rate at which work is being done, in an activity as a function of the applied effort and resource outlay. As a consequence, both the resource expenditure and the work done can be tracked within a network as a function of time.     

基于EMD与DVG的非线性时间序列预测模型及其应用研究

针对具有非线性和不稳定性的时间序列,提出一种结合经验模态分解(EMD)、有向可见图(DVG)网络的动态预测模型。利用经验模态分解将原时间序列分解为多个固有模态函数(IMF),然后对分解后的高频和低频IMF利用快速傅里叶变换得到各自的周期;依据每个周期,从原时间序列的尾部截取长短不一的子序列,然后采用有向可见图算法转换为多个有向网络,利用随机游走在每个有向网络中寻找与时间序列最后一个节点相似的节点;最后,依据平行线法,预测时间序列的下一个数值。原油价格的时间序列是一类典型的具有非线性和不稳定性的序列,利用此模型对WTI原油每日价格进行实证分析。研究结果表明,此模型不但可以有效地预测时间序列的变化趋势,而且具有较高的预测精度。     

Robustness of power-law networks: its assessment and optimization

Many practical complex networks, such as the Internet, WWW and social networks, are discovered to follow power-law distribution in their degree sequences, i.e., the number of nodes with degree \(i\) in these networks is proportional to \(i^{-\beta }\) for some exponential factor \(\beta > 0\). However, these networks also expose their vulnerabilities to a great number of threats such as adversarial attacks on the Internet, cyber-crimes on the WWW or malware propagations on social networks. Although power-law networks have been found robust under random attacks and vulnerable to intentional attacks via experimental observations, how to better understand their vulnerabilities from a theoretical point of view still remains open. In this paper, we study the vulnerability of power-law networks under random attacks and adversarial attacks using the in-depth probabilistic analysis on the theory of random power-law graph models. Our results indicate that power-law networks are able to tolerate random failures if their exponential factor \(\beta \) is \(<\)2.9, and they are more robust against intentional attacks if \(\beta \) is smaller. Furthermore, we reveal the best range \([1.8, 2.5]\) for the exponential factor \(\beta \) by optimizing the complex networks in terms of both their vulnerabilities and costs. When \(\beta < 1.8\), the network maintenance cost is very expensive, and when \(\beta > 2.5\) the network robustness is unpredictable since it depends on the specific attacking strategy.     

Stochastic Measures of Network Resilience: Applications to Waterway Commodity Flows

Given the ubiquitous nature of infrastructure networks in today's society, there is a global need to understand, quantify, and plan for the resilience of these networks to disruptions. This work defines network resilience along dimensions of reliability, vulnerability, survivability, and recoverability, and quantifies network resilience as a function of component and network performance. The treatment of vulnerability and recoverability as random variables leads to stochastic measures of resilience, including time to total system restoration, time to full system service resilience, and time to a specific α% resilience. Ultimately, a means to optimize network resilience strategies is discussed, primarily through an adaption of the Copeland Score for nonparametric stochastic ranking. The measures of resilience and optimization techniques are applied to inland waterway networks, an important mode in the larger multimodal transportation network upon which we rely for the flow of commodities. We provide a case study analyzing and planning for the resilience of commodity flows along the Mississippi River Navigation System to illustrate the usefulness of the proposed metrics.     

中国证券市场中Beta系数的存在性及其相关特性研究

本文认为,中国证券市场存在资本资产定价模型中描述的Beta系数,本文发现,使用不同市场收益率的算法计算出来的Beta系数有着显著的差异。因此,存在以不同的方法计算得到的Beta系数,在相同的研究过程中得出不相同的结果的情况可能会出现。本文的研究结果证实了这样一个事实:在中国证券市场,至少是在本文研究的时间区间段,CAPM模型是成立的。本文还发现,中国证券市场中Beta系数并不存在显著的行业差异,但是在按照是否被纳入计算成份类指数的标准将股票进行分类,即分为成份股和非成份股,这两大类股票的Beta系数存在显著的差异;本文还发现,在中国证券市场中,几乎不存在支持资本资产定价模型中的无风险收益率的参数。     

Longitudinal data analysis: Applications of random coefficient modeling to leadership research

Understanding how leaders develop, adapt, and perform over time is central to many theories of leadership. However, for a variety of conceptual and methodological reasons, such longitudinal research remains uncommon in the leadership domain. The purpose of this paper is to introduce the leadership scholar to conceptual issues involved in longitudinal design and analysis, and then demonstrate the application of random coefficient modeling (RCM) as a framework capable of modeling longitudinal leadership data. The RCM framework is an extension of the traditional regression model, so many readers will already have the fundamental knowledge required to use RCM. However, RCM has the additional capability of analyzing the kinds of data commonly found in longitudinal studies, including correlated observations, missing data, and heterogeneity over time. Further, the RCM allows for testing predictors of change over time. Thus, we introduce conceptual issues related to longitudinal research, discuss RCM within the context of regression, and conclude with an application of the RCM approach. We use a common substantive example throughout the paper to facilitate our discussion of the RCM.