时间贝叶斯网络及其概率推理

针对贝叶斯网络应用中出现的循环和动态问题,研究贝叶斯网络的时间扩展.给出了时间贝叶斯网络的定义;探讨了时间贝叶斯网络中环的存在合理性判断问题;给出了时间贝叶斯网络的概率推理算法,应用示例说明了方法的可行性.     

中国影子银行违约风险和防范机制研究——来自上市公司委托贷款数据的经验证据

本文运用中国上市公司披露的委托贷款公告数据，实证研究了影子银行的违约风险及其防范机制。数据显示，我国委托贷款的整体违约率为10.09%，远高于同期银行业金融机构的不良贷款率。进一步研究发现，与影子银行风险受信息因素影响的直觉一致，抵押条款和借贷距离会显著影响委托贷款违约率：其一，从抵押视角来看，抵押条款和贷款违约率显著正相关，这表明，为了防范事后的道德风险问题，贷款者会要求借款者提供抵押；其二，从借贷距离视角看，与近距离借贷（或同省借贷）相比，远距离借贷（或异省借贷）的违约风险相对较高，这揭示出，借贷距离越远，贷款者越难对借款者进行甄别和监督，从而推高了借款企业的违约概率。本文研究不仅为我国委托贷款这一影子银行机制的风险状况提供了直接的经验证据，而且对影子银行参与者如何有效防范风险和相关政府部门加强监管具有重要的借鉴意义。     

ROBUSTNESS OF PROCEDURES FOR THE BEHRENS-FISHER PROBLEMS: EXTENSION TO BIVARIATE NORMAL MIXTURES

In the applied sciences, it is often important to be able to compare the mean values of two populations. However, testing a hypothesis can be complex, if the two populations are heteroscedastic and exhibit non-normality in the data. This paper reviews currently available strategies for the multivariate Behrens-Fisher problem. It then carries out Monte Carlo comparisons of selected procedures to assess their robustness when applied to data from normal mixture distributions. The overall conclusion is that Johansen's procedure appears to work best for small sample data both in terms of empirical power and significance level. Johansen's procedure works reasonably well even with mixture data. The simulation also provides researchers with specific guidelines to follow at the early designing and planning stages of the investigation.     

空中防撞系统避撞机制的数学模型

在TCAS系统中,到达最接近点的时间Tau、HMD和VMD是描述空中碰撞物理过程的主要参数,利用该组参数能够完整地描述TCAS系统的防撞机制。该文通过对到CPA时间的近似,引入对Tau时间的物理解释;并通过坐标变换,采用本机和入侵飞机的相对距离、相对距离变化率和相对距离加速度推导出了HMD的数学表达式;分析了工程实际应用中的修正模型。     

Connectivity in urbanizing landscapes: The importance of habitat configuration,urban area size,and dispersal

Human activities affect both the amount and configuration of habitat. These changes have important ecological implications that can be measured as changes in landscape connectivity. I investigated how urbanization interacts with the initial amount and aggregation of habitat to change dispersal potential, restoration potential, and the risk of spatially extensive disturbances. I used a factorial set of simulated landscapes and subjected each landscape to habitat loss by overlaying 66 different US urban areas. I used a common connectivity metric, CONNECT, to assess the magnitude and direction of changes for a range of dispersal distances. My results show that the relationship between habitat loss and connectivity loss is non-linear and subject to interactions between the spatial patterns of habitat distribution, urban morphology, and dispersal capabilities. The implications of a given urban form vary widely as a function of habitat distribution and dispersal capabilities. This implies that impact assessments, restoration activities, and conservation planning should consider historical habitat distribution when evaluating observed changes in connectivity. While my results clearly show that more aggregated or continuous habitats are more vulnerable to connectivity loss, this approach can also be used to identify landscapes where restoring connectivity will be particularly effective, for example through placement of stepping stone habitats.     

Robust Methods of Building Regression Models—An Application to thè Housing Sector

This article studies robustification strategies for the linear model in the presence of outliers. The advantages of an internal analysis of the robustness of least squares for a given sample are pointed out. The application of this methodology is illustrated by building an explicit model of the determinants of rental housing values in the Madrid Metropolitan Area.     

在开拓中创新: 英国远程教育的经验与启示

以英国开放大学为标志的英国远程教育在世界上享有很高声誉,30年的办学实践使他们积累了丰富的经验。特别是在编制教材、对学生的支持服务、现代教育技术的应用、远程教学管理等方面有独到之处。中国的远程教育尤其是电大教育应该很好地借鉴英国在远程教育方面的经验,这对于推动我国电大教育的改革和创新有着重要的现实意义。     

“于是”与事理承接

以往对承接复句的分析说明主要是从时间关系或顺序入手的。以新的视角从逻辑意义入手 ,可将承接复句分为时间承接与事理承接两类。综合考察“于是”连接的“事理承接”复句的语义、语法与语用 ,可发现 :前后逻辑语义的密切相关、动态性、完成性与描写性是这类承接复句的主要特征。     

基于自动机模型数据关联性能评估算法

提出了一种基于自动机理论的性能评估方法,通过在有限自动机模型中增加描述观测的时间序列,来扩展其对数据关联过程的表达能力;使用时序有限自动机模型来描述关联处理算法的模型;使用带时间属性的字符串表示目标航迹。对数据关联的时序有限自动机模型进行一致性和可达性分析,并在此基础上给出了性能评估算法。实验结果证明该方法可以有效地评价关联算法的性能。