大数据背景下网络调查样本的建模推断问题研究——以广义Boosted模型的倾向得分推断为例

随着大数据和网络的不断发展，网络调查越来越广泛，大部分网络调查样本属于非概率样本，难以采用传统的抽样推断理论进行推断，如何解决网络调查样本的推断问题是大数据背景下网络调查发展的迫切需求。本文首次从建模的角度提出了解决该问题的基本思路：一是入样概率的建模推断，可以考虑构建基于机器学习与变量选择的倾向得分模型来估计入样概率推断总体；二是目标变量的建模推断，可以考虑直接对目标变量建立参数、非参数或半参数超总体模型进行估计；三是入样概率与目标变量的双重建模推断，可以考虑进行倾向得分模型与超总体模型的加权估计与混合推断。最后，以基于广义Boosted模型的入样概率建模推断为例演示了具体解决方法。     

高职学生网上评教数据的修正与优化处理研究

针对高职学生网上评教存在的问题,采用评教验证机制设置不合理评教的限制。对学生评教数据先剔除异常值,再分别对不同班级、不同课程和不同院系之间的学生评教数据进行修正与优化处理,得出最终的修正分值,降低了因班级、课程和院系的不同而导致的评教数据的差异性,使学生的网上评教能更准确有效的反应出教师的教学水平。     

Estimating E-bayesian and hierarchical bayesian of scalar parameter of gompertz distribution under type II censoring schemes based on fuzzy data

In this study, the E-Bayesian and hierarchical Bayesian of the scalar parameter of a Gompertz distribution under Type II censoring schemes were estimated based on fuzzy data under the squared error (SE) loss function and the efficiency of the proposed methods was compared with each other and with the Bayesian estimator using Monte Carlo simulation.     

大数据背景下基于社交网络的聚类随机游走抽样算法研究

数字经济时代,社交网络作为数字化平台经济的重要载体,受到了国内外学者的广泛关注。大数据背景下,社交网络的商业应用价值巨大,但由于其网络规模空前庞大,传统的网络分析方法 因计算成本过高而不再适用。而通过网络抽样算法获取样本网络,再推断整体网络,可节约计算资源, 因此抽样算法的好坏将直接影响社交网络分析结论的准确性。现有社交网络抽样算法存在忽略网络内部拓扑结构、容易陷入局部网络、抽样效率过低等缺陷。为了弥补现有社交网络抽样算法的缺陷,本文结合大数据社交网络的社区特征,提出了一种聚类随机游走抽样算法。该方法首先使用社区聚类算法将原始网络节点进行社区划分,得到多个社区网络,然后分别对每个社区进行随机游走抽样获取样本网 络。数值模拟和案例应用的结果均表明,聚类随机游走抽样算法克服了传统网络抽样算法的缺点,能够在降低网络规模的同时较好地保留原始网络的结构特征。此外,该抽样算法还可以并行运算,有效提升抽样效率,对于大数据背景下大规模社交网络的抽样实践具有重大现实意义。     

Developing ethical approaches to data and civil society: from availability to accessibility

This research note reflects on the gaps and limitations confronting the development of ethical principles regarding the accessibility of large-scale data for civil society organizations (CSOs). Drawing upon a systematic scoping study on the use of data in the United Kingdom (UK) civil society, it finds that there are twin needs to conceptualize accessibility as more than mere availability of data, as well as examine the use of data among CSOs more generally. In order to deal with the apparent “digital divide” in UK civil society – where, despite extensive government rhetoric about data openness, organizations face not only the barriers of limited time, funds, and expertise to harness data but also the lack of representation within existing data – we present a working model in which ethical concerns accompanying data utilization by civil society may be better accounted. This suggests there is a need for further research into the nexus of civil society and data upon which interdisciplinary discussion about the ethical dimensions of engagement with data, particularly informed by insight from the social sciences, can be predicated.     

Toward an integrated Bayesian network approach to measurement error detection and correction

In this article, the quality of data produced by national statistical institutes and by governmental institutions is considered. In particular, the problem of measurement error is analyzed and an integrated Bayesian network decision support system based on non-parametric Bayesian networks is proposed for its detection and correction. Non-parametric Bayesian networks are graphical models expressing dependence structure via bivariate copulas associated to the edges of the graph. The network structure and the misreport probability are estimated using a validation sample. The Bayesian network model is proposed to decide: (i) which records have to be corrected; (ii) the kind and amount of correction to be adopted. The proposed correction procedure is applied to the Banca d’Italia Survey on Household Income and Wealth and, specifically, the bond amounts are analyzed. Finally, the sensitivity of the conditional distribution of the true value random variable given the observed one to different evidence configurations is studied.     

Using logic model and visualization to conduct portfolio evaluation

Portfolio evaluation is the evaluation of multiple projects with a common purpose. While logic models have been used in many ways to support evaluation, and data visualization has been used widely to present and communicate evaluation findings, adopting logic models for portfolio evaluation and using data visualization to share findings simultaneously is surprisingly limited in the literature. With the data from a sample portfolio of 209 projects which aims to improve the system of early care and education (ECE), this study illustrated how to use logic model and data visualization techniques to conduct a portfolio evaluation by answering two evaluation questions: “To what extent are the elements of a logic model (strategies, sub-strategies, activities, outcomes, and impacts) reflected in the sample portfolio?” and “Which dominant paths through the logic model were illuminated by the data visualization technique?” For the first question, the visualization technique illuminated several dominant strategies, sub-strategies, activities, and outcomes. For the second question, our visualization techniques made it convenient to identify critical paths through the logic model. Implications for both program evaluation and program planning were discussed.     

Not just a number? NEETs,data and datalogical systems

This paper draws on empirical research with NEET populations (16–24-year-olds not in education, employment or training) in the U.K. in order to engage with issues around identification, data and metrics produced through datalogical systems. Our aim is to bridge contemporary discourses around data, digital bureaucracy and datalogical systems with empirical material drawn from a long-term ethnographic project with NEET groups in Leeds, U.K. in order to highlight the way datalogical systems ideologically and politically shape people’s lives. We argue that NEET is a long-standing data category that does work and has resonance within wider datalogical systems. Secondly, that these systems are decision-making and far from benign. They have real impact on people’s lives – not just in a straightforwardly, but in obscure, complex and uneven ways which makes the potential for disruption or intervention increasingly problematic. Finally, these datalogical systems also implicate and are generated by us, even as we seek to critique them.     

Data Science: A Powerful Catalyst for Cross-Sector Collaborations to Transform the Future of Global Health—Developing a New Interactive Relational Mapping Tool (Demo)

ABSTRACT

The increasingly complex and rapidly changing global health and socioeconomic landscape requires fundamentally new ways of thinking, acting, and collaborating to solve growing systems challenges. Cross-sectoral collaborations between governments, businesses, international organizations, private investors, academia, and nonprofits are essential for lasting success in achieving the Sustainable Development Goals (SDGs), and securing a prosperous future for the health and well-being of all people (United Nations, n.d United Nations. (n.d.). SDGs: Sustainable development knowledge platform. Sustainable Development United Nations. Retrieved from https://sustainabledevelopment.un.org/ [Google Scholar].). Our aim is to use data science and innovative technologies to map diverse stakeholders and their initiatives around SDGs and specific health targets—with particular focus on SDG 3 (Good Health & Well Being) and SDG 17 (Partnerships for the Goals)—to accelerate cross-sector and multidisciplinary collaborations. Initially, the mapping tool focuses on Geneva, Switzerland as the world center of global health diplomacy with over 80 key stakeholders and influencers present. As we develop the next level pilot, we aim to build on users’ interests, with a potential focus on non-communicable diseases (NCDs) as one of the emerging and most pressing global health issues that requires new collaborative approaches. Building on this pilot, we can later expand beyond only SDG 3 to other SDGs.