Bayesian density regression for discrete outcomes

We develop Bayesian models for density regression with emphasis on discrete outcomes. The problem of density regression is approached by considering methods for multivariate density estimation of mixed scale variables, and obtaining conditional densities from the multivariate ones. The approach to multivariate mixed scale outcome density estimation that we describe represents discrete variables, either responses or covariates, as discretised versions of continuous latent variables. We present and compare several models for obtaining these thresholds in the challenging context of count data analysis where the response may be over‐ and/or under‐dispersed in some of the regions of the covariate space. We utilise a nonparametric mixture of multivariate Gaussians to model the directly observed and the latent continuous variables. The paper presents a Markov chain Monte Carlo algorithm for posterior sampling, sufficient conditions for weak consistency, and illustrations on density, mean and quantile regression utilising simulated and real datasets.     

Every Minute Counts: Using Process Improvement and Performance Feedback to Improve Patient Flow in an Emergency Department

Prolonged emergency department (ED) visits are associated with a number of adverse outcomes for patients as well as lower patient satisfaction scores and increased costs. Several factors that influence the length of ED visits are out of the control of hospital employees, but some opportunities exist to improve performance. For this study, the ED department of a 150-bed hospital in the southeastern United States wanted to improve door-to-discharge time. To do so, a subprocess of door-to-discharge time was targeted, door-to-order. After analyzing the process, the team created standard orders for the 10 most common presenting conditions in the ER with preapproval, allowing nurses to submit the orders without the provider first visiting the patient. Following the process change, daily feedback was added to increase utilization of the preapproved orders. Reductions in door-to-order times and door-to-discharge were observed and patient satisfaction remained stable. Implications for future research in this area are discussed.     

Using Lean Six Sigma to improve mobile order fulfilment process in a telecom service sector

This study proposes and follows a specific and systematic framework for implementing Lean Six Sigma (LSS) methodology in a telecom company in order to improve customer satisfaction by minimizing the company’s response time to customer requirements. The goal of this study was achieved by utilizing several LSS tools under five phases of the DMAIC methodology. Unlike previous studies in the telecom sector that used only qualitative method, in this study, both qualitative and quantitative methods were utilized to draw meaningful conclusions. As a result of the implementation of the LSS methodology, the average order fulfilment lead time for sales orders (SO) and value-added service (VAS) orders was reduced from 10.3 to 5.9 days and from 1.5 to 0.5 days, respectively. The reduction in lead time resulted in an increase in the sigma level for SO and VAS orders from 0.44 to 1.26 and from 0.73 to 2.66, respectively. These improvements were expected to lead to a financial benefit in savings of over $600,000 per year in operational costs, enhancements to customer experience and an increase in revenue generating opportunities. Moreover, this article enriches the existing literature on the application of LSS concept in the service industry, and helps the company to speed up the response to customer requirements.     

目标导向层次分析方法

对含有抽象属性的多属性层次结构而言,层次分析法即AHP（包括DIS-AHP、ABS-AHP、IDE-AHP和SUP-AHP四种具体方法）会因比率比较基准缺失、权重内涵模糊不清或方案评价不保序而缺乏科学理性。为发展AHP,基于摆幅置权（SW）判断模式和多属性决策属性价值公度方法,首先给出了能为层次结构抽象属性上的SW判断提供支持的规约性多属性决策属性价值公度方法,然后由此并结合多属性价值理论给出了能够克服现有层次分析法内在缺陷的目标导向层次分析方法即ToAHP。相对于AHP,ToAHP在判断模式与权重内涵、方法建构的理论基础和相关假设检验、方案评价保序与其内在数理依据上具有明显的相对科学合理性。应用分析表明：在输入信息可比的条件下,ToAHP明显优于AHP的四种分析方法之中最具可信性的SUP-AHP方法。     

基于Hawkes因子模型的股价共同跳跃研究

本文首先比较了三种目前主流的共跳检验方法：基于LM检验的共跳检验、BLT共跳检验和FHLL共跳检验,结果表明,三种方法在识别共跳数量上差距明显,但三者结果的重合部分基本属于市场暴涨暴跌行情,说明共跳识别对市场剧烈波动的聚集性较为敏感。基于跳跃、共跳存在的聚集性问题,本文将Hawkes过程引入跳跃和共跳的研究,构建了基于Hawkes过程的因子模型,结果显示,基于Hawkes因子模型的MJ统计量、CJ统计量和实证数据的拟合程度较好,表明因子模型能够更好地描述跳跃和共跳的聚集性。     

基于Hawkes过程中美股市大幅波动互激效应的研究

近年来,由于中美经济联系日趋紧密,中美股票市场大幅波动的互激效应明显增强。本文考虑中美股市时差和法定节假日差异等因素,运用标值Hawkes过程对2006-2017年CSI300和S&P500大幅波动收益率数据进行建模,结果表明：（1）中美股市大幅波动互激效应存在不对称性,美股市场大幅波动对中国股市的互激效应更强;（2）中美股市大幅波动的幅度对互激效应不存在显著影响;（3）中美股票市场对于大幅波动互激效应的消化速度存在差异,中国股票市场消化美股大幅波动互激效应的速度较快。本研究对金融市场监管者和投资者均有一定意义。     

面向服务的复杂成形装备产品架构设计与优化

复杂成形装备作为高端制造产业的基础装备,是各产业转型升级和技术进步的重要保障。同时快速发展的互联网与大数据等新兴信息技术已经成为装备制造业创新不可或缺的组成部分,极其深刻地影响着复杂成形装备产业的制造模式、发展战略以及产品的开发方式。本文研究了面向服务的复杂成形装备产品架构设计与优化方法。采用公理化设计的域结构思想,建立需求域、功能域和架构域之间的映射关系;提出了基于QFD的功能生成方法以及功能模型约简方法;利用DMM建立产品架构和服务架构之间的关联关系;利用模块化理论方法,并考虑成本因素对产品架构进行优化。     

科技查新业务流程的再造

对科技查新工作的流程进行了分析,指出其适合于进行流程再造的特点,据此提出了科技查新流程再造的目标、科技查新管理信息平台构建的层次结构和功能模块划分,最后给出了流程再造不同阶段的任务.     

创建黑水城出土文献研究新的里程碑

黑水城文书是20世纪继甲骨文、汉晋简牍、敦煌文书以后的又一次重大出土文献发现。对于这批珍贵文献,史金波从文物、文献和史料以及学术等三个方面对其价值进行探讨的同时,指出了在录文、定名和断代过程中需要注意的问题,并对黑水城出土汉文文献的研究情况作了探讨。白滨从文献出土地辨析与文献甄别、文献缀合以及文献残卷的拟题与断代等三个问题入手,以现有的研究成果为个例对黑水城文献整理与研究过程中应该注意的问题作了解析。孙继民对文献的朝代构成和学科定名问题进行探讨后认为,黑水城文献的朝代构成中可确定的是唐、五代、辽、宋、西夏、金、伪齐、元(包括北元)诸朝;目前流行的"西夏学"一语不足以涵盖黑水城文献的性质,围绕黑水城文献而兴起的专门学问用"黑城学"或"黑水城文献学"定名更为恰当;此外,他还对"黑城学"与"西夏学"的关系进行了辨析。杨倩描认为,俄藏黑水城宋代军政文书不仅可以对两宋之际以鄜延路为中心的西北地区史料作一定的补充,而且对一些具有普遍意义的宋代制度、事件、人物的研究也有相当的价值。     

体系构建:高师院校文化素质教育的着力点

高等学校的文化素质教育工作,已成为高等学校教育教学改革的一项重要内容,是广大师生共同关心和参与的一项重要工作,亦是高等学校注重素质教育的核心内容之一。然而,真正要将文化素质教育落实到高等学校教育教学改革的实际中,还有一些问题需要进一步加以明确。本文对高师院校文化素质教育开展的缘起、重要意义、工作的着力点以及实施途径进行了梳理和探讨。