基于DEA的交通运输与经济发展的协调性评价

数据包络分析法(DEA)是利用多个输入指标和多个输出指标的数据,对具有可比性的一些"单位"或"部门"(称为"决策单元")进行相对效率评价,应用于对交通运输和经济发展的协调性的动态综合评价,实际是对两个系统相互支持和利用的相对有效性进行动态评价,其评价结果可以通过计量回归模型来验证,即应用Chow's断点(Breakpoint)检验,从交通运输与经济发展计量模型结构发生显著变化的角度,可以进一步验证交通运输与经济发展之间协调性的动态变化趋势.     

大数据时代对传统统计学变革的思考

本文在大数据时代背景下,将统计学与大数据有机地结合,剖析了大数据时代给统计学带来的变革,阐述了大数据为传统统计学带来的发展机遇。在大数据时代,为了保持统计学旺盛的生命力,本文对统计学的发展提出了几点思考。     

基于机器学习LSTM&US模型的消费者信心指数预测研究

消费者信心指数等宏观经济指标具有时间上的滞后效应和动态变化的多维性,不易精确预测。本文基于机器学习长短时间记忆(Long Short-Term Memory,LSTM)神经网络模型,结合大数据技术挖掘消费者信心指数相关网络搜索数据(User Search,US),进而构建一种LSTM&US预测模型,并将其应用于对我国消费者信心指数的长期、中期与短期的预测研究,同时引入多个基准预测模型进行了对比分析。结果发现:引入网络搜索数据能够提高LSTM神经网络模型的预测性能与预测精度;LSTM&US预测模型具有较好的泛化能力,对不同期限的预测效果均较稳定,其预测性能与预测精度均优于其他六种基准预测模型(LSTM、SVR&US、RFR&US、BP&US、XGB&US和LGB&US);预测结果显示本文提出的LSTM&US预测模型具有一定的实用价值,该预测方法为消费者信心指数的预测与预判提供了一种新的研究思路,丰富了机器学习方法在宏观经济指标预测领域中的理论研究。     

基于蝙蝠算法SVR模型的北京市二手房价预测研究

传统SVR模型可预测房价变化趋势,但不恰当的参数设置会影响预测的精度。本文针对北京二手房同比价格指数的非线性变化特征,将蝙蝠算法(BatAlgorithm,BA)引入到SVR模型中,使其对模型的三个参数进行优化设置,结合网络搜索数据(Web Search Data,WSD),构建了BA-SVR&WSD混合模型,并给出了该模型算法的预测流程,通过引入多个基准预测模型和预测性能度量指标进行对比研究。研究结果表明：基于蝙蝠算法的SVR模型的具有较好的泛化能力、预测效果更准确且预测精度更高,该预测方法也为北京二手房价格的监测和调控提供有价值的参考。     

数据包络分析方法的灵敏度分析

本文对数据包络分析方法的有效决策单元作了灵敏度分析。文中首先提出一种只考虑乎一投入量变化时的灵敏度分析方法,然后在此基础上研究几个报入量同时变化时的灵敏度分析。进而扩展到产出量变化投入产出量同时变化时的灵敏度分析,最后用数例进行了说明。     

大数据时代的统计教育

2014年11月,美国统计学会适应大数据时代的要求,发布了统计学本科专业指导性教学纲要。而在2013年,我国统计类本科专业刚刚进行了一次较大调整,目前的专业课程设置和教学内容改革还处于探索阶段。美国统计学会发布的这份指导性教学纲要对于推进我国统计类本科专业教育改革具有重要借鉴意义。本文首先概括性地介绍了美国统计学会发布的统计学本科专业指导性教学纲要的核心内容,包括统计专业本科生应该掌握的基本技能和应该修读的主要课程,然后分析了我国统计类本科专业教育存在的问题,并提出了在大数据时代改进我国统计类本科专业教育的几点建议。     

基于DEA的封闭式基金业绩评价

数据包络分析(Data Envelopment Analysis,DEA)是一种广泛运用于相对绩效评估的系统分析方法,本文将一多输入单输出DEA模型引入证券投资基金业绩评价,其中输出为基金收益,而输入则为管理费用、交易成本和标准差。随后,利用该模型对2000年以前上市的20只基金在2000年、2001年及2000～2001年间的业绩进行了评价,主要结论有:在所有评价期,基金安顺、普丰、兴和和金鑫的业绩相对有效,基金裕阳和裕隆相对较无效,它们的相对业绩均表现短期持续性;单位交易成本和基金收益率而非单位管理费用和标准差是影响基金相对业绩(非绝对业绩)的主要因素,尤其是基金收益率。     

Exploring the efficiency of Mexican universities: Integrating Data Envelopment Analysis and Multidimensional Scaling

National policy initiatives require the expenditure of large amounts of resources over several years. It is common for these initiatives to generate large amounts of data that are needed in order to assess their success. Educational policies are an obvious example. Here we concentrate on Mexico׳s “Educational Modernisation Programme” and try to see how this plan has affected efficiency in teaching and research at Mexico׳s universities. We use a combined approach that includes traditional ratios together with Data Envelopment Analysis models. This mixture allows us to assess changes in efficiency at each individual university and explore if these changes are related to teaching, to research, or to both. Using official statistics for 55 universities over a six year period (2007–2012), we have generated 12 ratios and estimated 21 DEA models under different definitions of efficiency. In order to make the results of the analysis accessible to the non-specialist we use models that visualise the main characteristics of the data, in particular scaling models of multivariate statistical analysis. Scaling models highlight the important aspects of the information contained in the data. Because the data is three-way (variables, universities, and years) we have chosen the Individual Differences Scaling model of Carroll and Chang. We complete the paper with a discussion of efficiency evolution in three universities.     

An integrated model for slack-based measure of super-efficiency in additive DEA

As a non-radial approach, a super-efficiency model, Super SBM, was proposed by Tone [15] to rank efficient DMUs. Du et al. [7] extends the Super SBM model to the additive (slacks-based) DEA model. To obtain the super-efficiencies of the DMUs, one needs to identify the efficient DMUs first and then apply the additive super-efficiency model to those efficient DMUs. In this paper, we propose an integrated model so that the efficiencies of the inefficient DMUs and the super-efficiencies of the efficient DMUs can be obtained by a single model. The efficiency scores obtained by our integrated model are the same as those obtained by Du et al. [7] and the additive DEA model.     

A fair evaluation of certain stage in a two-stage structure: revisiting the typical two-stage DEA approaches

The efficiency of decision processes with a two-stage structure has been studied by some modified versions of Data Envelopment Analysis (DEA) methodology, such as the relational or centralized model, and the non-cooperative model. After revisiting the rationale of the centralized model provided by the literature, we find that some unfairness exist in its efficiency evaluation of certain stage. This unfairness leads to the usual underestimation of the overall efficiency by the centralized model. Furthermore, because the independent DEA model for one stage ignores its relation and coordination with the other stage and the two-stage system, externalities between these members may arise and lead to the seeming contradiction in efficiencies derived by independent DEA models for the stages and the black box system. Therefore, we argue that the efficiency of certain stage in the context of a two-stage structure should be reevaluated instead of simply using the independent DEA model. A sequence of leader-follower procedures, with data adjustment on intermediates, is proposed to eliminate the externalities and to ensure a fair evaluation. We find that, after this data adjustment, the reevaluation of the second stage for a given Decision Making Unit (DMU) yields the same result as obtained by the standard DEA model regarding the two-stage as a black box. Moreover, some explicit relations are established between the black box model, the centralized model, and the non-cooperative model. Two typical examples taken from the literature illustrate our main results. Our findings also imply that more emphasis should be placed on the game theoretic DEA approach to model the efficiency evaluation of two-stage processes.