On the choice of instruments in mixed frequency specification tests

Abstract

Time averaging has been the traditional approach to handle mixed sampling frequencies. However, it ignores information possibly embedded in high frequency. Mixed data sampling (MIDAS) regression models provide a concise way to utilize the additional information in high-frequency variables. In this paper, we propose a specification test to choose between time averaging and MIDAS models, based on a Durbin-Wu-Hausman test. In particular, a set of instrumental variables is proposed and theoretically validated when the frequency ratio is large. As a result, our method tends to be more powerful than existing methods, as reconfirmed through the simulations.     

Enhancing a Randomized Response Model to Estimate Population Means to Sensitive Questions

ABSTRACT

Candidate parametric mortality models are tested graphically. If the model is correct, the transformed data are distributed exponentially. The graphical test is based on scale and space inference. It involves smoothing of the hazard rate and simultaneous confidence intervals. It is applied to a frailty model used to set annuity reserves. Simulation and the comparison with other non-graphical tests shows that the graphical test helps localize discrepancies of empirical data with respect to the tested model.     

可变产能的按订单装配系统库存和生产决策研究

本文基于一个ATO 生产商的实践,考虑一个需求不确定并具有子装配件的单周期ATO 系统,为了应对较长的采购提前期和有限产能的挑战,生产商可以在得到确定的需求之前提前采购零件,装配子装配件以至于最终产品。由于产品物料清单结构中存在子装配件作为可选的中间件,因此完全使用零件和使用子装配件装配最终产品的不同,造成装配能力在时间上具有可变性。我们对此问题建立了利润最大化模型,分析在上述ATO 环境中的最优库存和生产决策。通过一系列最优解的性质,我们得到了该问题的有效解决方法。     

一种基于不确定语言变量的房地产投资风险评价方法

房地产风险评价是房地产项目管理的重要组成部分,对降低企业风险,提高企业核心竞争力具有重要作用。采用专家打分法,基于房地产项目开发阶段建立房地产投资风险评价指标体系,并根据评价指标的模糊性和不确定多准则决策理论,建立基于不确定语言变量的房地产投资风险评价方法。实证研究表明,该评价指标体系和评价方法是有效的,为房地产企业开展投资风险评估提供了一种可行的方法。     

外商在华直接投资区位选择影响因素实证分析

当前,外商直接投资在我国存在着明显的地区分布失衡问题,为此重点研究吸引外资选择投资区位的决定性因素。运用回归模型,对我国各省区2009年的截面数据进行了实证分析,结果表明:市场规模、工资水平、基础设施是吸引外商直接投资的主要因素,而劳动力素质在外商直接投资区位选择中的影响效果较小。这些因素对我国有效吸引外商直接投资具有重大启示。     

Distribution lot-sizing models for arborescent supply chains with discrete-period variable demand

This study formulates a novel mixed-integer programming lot-sizing model for arborescent supply chains with discrete-period variable demand and then develops an efficient two-phase heuristic method, in which a combined multi-period demand ordering policy, rather than the lot-for-lot ordering policy usually assumed in previous papers, is adopted. Two important properties are introduced and used to obtain a better initial feasible solution. The good performance of the proposed heuristic method is verified through a comparison with the optimal solution method. It is also shown that the performance of the proposed combined multi-period demand ordering method is superior to that of the lot-for-lot ordering method. Sensitivity analysis is conducted to explore the impacts of changing the values of relevant parameters on the total supply chain cost, the total number of orders and the total number of opened members. Finally, a well-known logistics company in Taiwan is chosen to demonstrate the excellent performance and the aptness of the proposed ordering method.     

杂合灰色聚类与变精度粗糙模糊集的概率决策方法及应用

在基于粗糙集理论或扩展粗糙集理论的不确定性决策中,仅由数据集无法获得决策表,同时由于决策属性呈现模糊性,以致于难以获取概率决策规则。针对这一类决策问题,基于灰色定权聚类与优势粗糙集变精度方法,本文构建了一种的杂合决策方法。该方法首先利用中心点三角白化权函数的灰色定权聚类方法将包含不同量纲指标的知识表示系统生成多属性决策表,而后运用变精度粗糙模糊集进行决策分析,生成概率决策规则,最后以区域关键技术的选择为例,表明该模型的可行性与实用性。     

Universal equation for the relative change in profit of manufacturing company

In contemporary conditions of the company's business operations, where high dynamics of costs, sales volume and change of production programme is present, it is of crucial importance to investigate their effects on the change of profit. Starting from cost–volume–profit equation, the aim is to arrive at a universal equation that will simultaneously measure a relative change in profit for a number of products, not only under the influence of change in sales volume but also of other relevant variables, such as sales price, fixed and variable costs. The basic hypothesis is that it is possible to establish in a form of universal equation the dependence between the change in profit and change in influential variables. In this investigation, first it was observed the partial influence of some variables on the change in profit and their dependence was determined for a single product, and then for more than one product. Finally, by summing up all those effects, a universal equation of profit change was obtained. The derived universal equation for the relative change in profit along with simultaneous effects of several variables makes possible for the company management to more simply determine the profit for diverse conditions of business operations. The universal equation for the relative change in profit was applied in one company and the results obtained confirm its significance.     

基于零膨胀分位数两部模型的银行贷款违约预测研究

贷款信用风险评估是银行风控的重要内容。贷款逾期天数作为常见的风险度量指标,具有典型的零膨胀特征。对于零膨胀数据,传统的线性回归不再适用,两部模型是常用的代表方法。考虑到贷款数据具有偏态分布特征,本文构建了一个分位数两部模型—logit-quantile模型。该模型由Logistic回归和分位数回归构成,为了进行风险因素的选择,在模型的两个回归中添加了Lasso惩罚。为了求解模型,本文采用了坐标下降法和线性规划法相结合的迭代算法。模拟分析显示,对比逐步法和常用的logit-linear两部模型,新模型表现出了最好的变量选择效果,尤其在零膨胀比例为80%及高维情形时,该模型的表现仍然最优。最后对某银行的贷款数据实证分析显示,新模型具有更精简的结构,采用交叉验证技术进行预测显示新模型的预测和分类表现最好。     

十年来中国抗争运动研究评述

上世纪90年代以来,中国的抗争运动爆发的频度和影响力不断增长,吸引了越来越多研究者的关注,海内外关于这一题域的研究也日渐兴起。这一研究题域在概念谱系上呈现出多元化的状态,以过程分析、结构分析和机制分析作为其主要的分析路径,以集体行动、日常抵抗、社会动员以及政治过程等理论为指导,并特别关注抗争运动与民主政治的关系;在研究方法上,规范性实证研究的比例正在上升,定量研究和比较研究是未来的发展方向。