基于fused惩罚的稀疏主成分分析

本文旨在研究基于fused惩罚的稀疏主成分分析方法，以适用于相邻变量之间高度相关甚至完全相等的数据情形。首先，从回归分析角度出发，提出一种求解稀疏主成分的简便思路，给出一种广义的稀疏主成分模型—— GSPCA模型及其求解算法，并证明在惩罚函数取1-范数时，该模型与现有的稀疏主成分模型——SPC模型的求解结果一致。其次，本文提出将fused惩罚与主成分分析相结合，得到一种fused稀疏主成分分析方法，并从惩罚性矩阵分解和回归分析两个角度，给出两种模型形式。在理论上证明了两种模型的求解结果是一致的，故将其统称为FSPCA模型。模拟实验显示，FSPCA模型在处理相邻变量之间高度相关甚至完全相等的数据集上的表现良好。最后，将FSPCA模型应用于手写数字识别，发现与SPC模型相比，FSPCA模型所提取的主成分具备更好的解释性，这使得该模型更具实用价值。     

A lost family-planning regime in eighteenth-century Ceylon

Based on Dutch colonial registers (thombos), this paper reconstructs fertility for two districts in Ceylon, 1756–68. It overcomes challenges in data quality by establishing the outer bounds of plausible estimates in a series of scenarios. Among these, total fertility rates (TFRs) averaged 5.5 in one district, but only 2.7 in the other. These figures exclude the victims of infanticide, a custom noted in European travelogues between about 1660 and 1820. Sex ratios among children differed depending on the number of older siblings, and overall, 27?per cent of girls are missing in one district and 57?per cent in the other. There was little significant variation either in the TFR or the sex ratio by socio-economic status, suggesting that poverty was not a key factor in motivating infanticides. Instead, we argue that at least parts of Ceylon had a forward-looking culture of family planning in the eighteenth century, which was lost in subsequent decades.     

环境信息披露的污染减排效应评估

本文利用我国2008年正式实施环境信息披露制度这一外生冲击构造准自然实验,基于2004-2017年我国285个城市的面板数据,通过双重差分法系统评估环境信息披露对工业污染物排放的影响。克服环境信息披露的测量困难与内生性问题,首次考察环境信息披露的污染减排效果,并借助数理模型对其影响机制进行规范阐释。研究发现,环境信息披露能够显著降低工业污染物排放水平,且该影响具有一定的时滞性和长期性;同时,减排作用会随地区环境污染程度和环境规制力度的增强而呈现递增规律;此外,机制分析的结果表明,其传导机制主要来自于产业结构转型和减排技术进步。为验证研究结论的稳健性,本文提供了平行趋势、工具变量、安慰剂等多种方法的检验结果。本文的研究在经验上丰富了环境信息披露与环境污染治理之间关系的相关讨论,为提升我国环境污染治理水平、打赢污染防治攻坚战提供有益的政策启示。     

Revisiting the gap between stylized and diary estimates of market work time

Previous studies find that workers of longer work weeks report more market hours in stylized measure than in time diary, while those of shorter work weeks report fewer hours. Using data from the American Time Use Survey (ATUS) 2003-2007, this paper attempts to explain this dilemma. I argue that market work time is composed of activity time, committed time, and constrained time. Thus, part of the difference found between the two estimates is due to the calculation of the diary estimate. I also argue that the wording of the stylized question is consequential. Some stylized questions (e.g., How many hours per week do you usually work?) might capture the mode, instead of the mean, of work time. Thus, when the distribution of work time is skewed, the mismatch between the two estimates is expected. A sequence-based identification for diary estimate and a non-parametric adjustment for stylized estimate are proposed and empirically examined. The result indicates that both methods significantly reduce the observed gap between the two estimates. I discuss the implications for future time use survey design in the concluding section.     

Efficient Estimation of Parameters of the Negative Binomial Distribution

In this article we investigate a class of moment-based estimators, called power method estimators, which can be almost as efficient as maximum likelihood estimators and achieve a lower asymptotic variance than the standard zero term method and method of moments estimators. We investigate different methods of implementing the power method in practice and examine the robustness and efficiency of the power method estimators.     

社会工作研究的人文精神——对以实证主义为导向的美国社会工作研究的批判

长期以来,国际社会工作研究常常倾向于以实证主义和经验主义为基础的研究导向,特别是在美国,基于证据的研究方法在社会工作领域十分流行。随着全球化的推进和人们生活方式的现代化,社会工作研究所面临的问题更为复杂,其解决方法单纯依靠各种技术处理的手段来展开是远远不够的,我们在讨论这些问题时,要强化其价值导向。这要求我们在讨论社会工作研究的问题上,把我们的关注点从证据、技术手段和职业标准扩展到价值观、人文精神和对全球化问题的关注等方面,以此来推进国际社会工作的发展。     

Stress,strain, coping and social support for affected family members attending the National Problem Gambling Clinic,London

Aims were: to compare burden experienced by affected family members (AFMs) attending a problem gambling treatment clinic in London, England with that of AFMs affected by substance problems; to examine socio-demographic correlates of AFM burden; to evaluate change following an intervention designed for AFMs; and to test the assumption of the stress-strain-coping-support (SSCS) model that change in AFM coping is important. AFMs (N = 215) completed a gambling version of the short questionnaire for family members affected by addiction (SQFM-AA) which assesses stressful impact, symptoms of ill health, ways of coping, social support and overall burden. All received a 5-Step Method workbook, based on the SSCS model. The SQFM-AA was repeated three to six months later (n = 96). T-test analyses showed that baseline burden and related variables were comparable to those of family members affected by substance problems, were greater for wives and those living in the same household as the gambling relative, and were significantly reduced at follow-up. Regression modelling indicated the importance, for AFMs’ health, of reduced levels of engaged-emotional coping. Family members affected by gambling, some subgroups especially, experience high levels of burden. They can benefit from a model-based intervention, and coping change may be an important process.     

月度工业生产发展速度指标解读：差异比较与经验启示 ——以OECD国家为例

 正确解读统计指标是准确理解和把握统计数据意义的关键所在。本文从指标的名称、定义、计算方法、空间规定和基础指标获得方式等方面，对OECD国家的工业生产发展速度指标进行了全面解读，以期从中得出经验与启示。     

Bivariate short distributions

The method of MML estimation for a univariate normal (Tiku 1967, 1973) is extended to a bivariate normal population. Thus, a theoretical foundation is given to the robust correlation coefficient proposed by Tiku and Balakrishnan (1986).     

分支蚁群动态扰动算法求解TSP问题

蚁群优化算法是一种求解组合优化难题的强启发式算法,它利用正反馈和并行计算原理,具备很强的搜索能力。近年来,蚁群优化算法广泛应用于TSP问题的研究。本文提出分支蚁群动态扰动(DPBAC)算法,该算法主要从5个方面对基本蚁群算法做出改进:引入分支策略选取出发城市;改进状态转移规则;引入变异策略改进蚂蚁路径;改进信息素更新规则;引入条件动态扰动策略。实验表明,该算法可以有效改善基本蚁群算法搜索时间较长、容易陷入局部极小等缺点。