固定效应部分线性变系数面板模型的快速有效估计

本文将最小二乘支持向量机(LSSVM) 和二次推断函数法(QIF) 相结合，为个体内具有相关结构的固定效应部分线性变系数面板模型提供了一种新的快速估计方法；在一定的正则条件下，论证了参数估计量的渐近正态性和非参数估计量的收敛速度；采用Monte Carlo模拟考察了估计方法在有限样本下的表现并将估计技术应用于现实数据分析。该方法不仅保证了估计的有效性和统计推断力，而且程序运行速度得到较大幅度提升。     

Meshworked reputation: Publicists’ views on the reputational impacts of online communication

This paper discusses the conceptual and empirical connections between an organization's reputation management and online communication. The paper develops a theory driven model of the structural dimensions of reputation and analyzes organizational communication professionals’ views on the potential that online communication has for reputation management. The survey data showed that online communication was perceived to have positive impacts on the structure and advantages of reputation, and that these two aspects would seem to be strongly dependent on each other. Thus, online communication can be used to influence the assessments made by stakeholders about an organization's products and services, corporate responsibility, success, its ability to change and develop, and its public image. In addition, online communication can generate reputational advantages by strengthening stakeholder relationships and building social capital for the organization.     

Is the medium the message? Perceptions of and reactions to crisis communication via twitter, blogs and traditional media

Value changes and the rapid emergence of media innovations (internet, social web) in society lead to an institutionalization of crisis communication, in which especially new media play a crucial role. The key contributions of the paper include deepening and refocusing the theoretical foundations of crisis communication by experimentally analyzing the effects of traditional and social-media strategies on the recipients’ perceptions of reputation; and by analyzing the effects or crisis responses on the recipients’ secondary crisis communications (e.g., sharing information and leaving a message) and reactions (e.g., willingness to boycott). The results indicated that the medium matters more than the message. For all three dependent measures - reputation, secondary crisis communication and reactions - main effects of medium occurred, whereas the message had only a significant main effect on secondary crisis reactions.     

Social Relations Model Analyses of Perceived Self‐Control and Trust in Families

How do people know which family member is trustworthy? In this study, the authors tested the hypothesis that people use their perception of a family member's self‐control as an indicator of his or her trustworthiness. Eighty‐four Dutch families consisting of 2 parents and 2 children completed questionnaires assessing each family member's trust in and perceived self‐control of the other 3 family members. This full‐family design enabled the authors to examine their hypothesis in horizontal relationships, between family members of equal status (i.e., parent–parent and sibling–sibling relationships), and vertical relationships, in which partners have unequal status (i.e., parent–child and child–parent relationships). Consistent with the hypothesis, Social Relations Model analyses showed that being perceived as having higher self‐control is related to greater trustworthiness among adults and children in the large majority of horizontal and vertical relationships (10 out of 12). These findings highlight that perceived self‐control is an important factor by which to gauge trustworthiness in families.     

General Sparse Boosting: Improving Feature Selection of L2 Boosting by Correlation-Based Penalty Family

In high-dimensional setting, componentwise L₂boosting has been used to construct sparse model that performs well, but it tends to select many ineffective variables. Several sparse boosting methods, such as, SparseL₂Boosting and Twin Boosting, have been proposed to improve the variable selection of L₂boosting algorithm. In this article, we propose a new general sparse boosting method (GSBoosting). The relations are established between GSBoosting and other well known regularized variable selection methods in the orthogonal linear model, such as adaptive Lasso, hard thresholds, etc. Simulation results show that GSBoosting has good performance in both prediction and variable selection.     

Model Selection Information Criteria in Latent Class Models with Missing Data and Contingency Question

Latent class analysis (LCA) has been found to have important applications in social and behavioral sciences for modeling categorical response variables, and nonresponse is typical when collecting data. In this study, the nonresponse mainly included “contingency questions” and real “missing data.” The primary objective of this research was to evaluate the effects of some potential factors on model selection indices in LCA with nonresponse data.

We simulated missing data with contingency questions and evaluated the accuracy rates of eight information criteria for selecting the correct models. The results showed that the main factors are latent class proportions, conditional probabilities, sample size, the number of items, the missing data rate, and the contingency data rate. Interactions of the conditional probabilities with class proportions, sample size, and the number of items are also significant. From our simulation results, the impact of missing data and contingency questions can be amended by increasing the sample size or the number of items.     

我国城乡居民消费行为差异研究

本文使用1978-2014年我国居民消费数据,研究城乡居民的消费总量、收支结构、平均消费倾向、边际消费倾向和恩格尔系数等差异,并选取31个省市的面板数据构建城乡消费模型进行分析。结果表明：①城乡居民消费行为可分三个阶段,城乡差距经历两个轮回,现在第二轮扩张期。②相对而言,农村居民收入低消费率高支出结构固化,对物价变动有滞后性和拖尾性,近期在城镇居民平均消费倾向持续走低时平稳走高。③城镇居民自发消费与边际消费倾向大致呈反比,同一城市的城乡居民自发消费与边际消费倾向相关性不强。文章建议,降低城乡交通通信类支出,扩大城乡家庭设备及用品类市场和农村文教娱乐类市场,提高农村居民健康及医疗保障水平。     

教育改善贫困效应的地区异质性研究

教育对于增加收入、改善贫困无疑是一个重要的途径。在目前多维贫困越来越受到重视的情况下,本文在收入贫困和多维贫困两种贫困识别标准下,分析了教育改善贫困的效应在地区之间的异质性,考察了该效应是否受地区经济发展的影响。根据分层LOGIT模型的估计,本文认为地区经济发展水平是发挥教育改善收入贫困效应的重要舞台,对于多维贫困的改善效应则不明显。本文得到的一个重要扶贫政策建议是要发挥教育改善贫困的效应,必须注重精准扶贫与发展地区经济相结合;但仅仅发展经济,不一定能保证教育对多维贫困的改善效应,减轻多维贫困需要更加重视公共产品供给和民生保证。     

包含加法模型和混合模型的指数分析体系

统计指数体系分析方法的一个较大不足就是局限于乘法形式的经济方程式,然而经济现象之间的相互联系是多种多样的,目前的统计指数体系分析方法难以应用于形式多样的复杂经济现象的因素分析。本文把基于乘法方式的指数体系称之为指数体系的“乘法模型”,并以此为基础,将传统的只包含乘法关系的经济方程式加以扩展,将其推广到可以应用于加减运算的“加法模型”和包含全部四则运算的“混合模型”,建立了“广义指数分析模型”。该模型不仅保留了传统统计指数体系的基本结构和基本分析方法,还可以较大地提高统计指数分析的深度和广度,由此可以基本解决统计指数体系分析方法的局限性问题。     

灾后社区重建中的社会工作介入——从地区发展模式的视域展开

本文立足于汶川灾后社区重建的现实,通过分析目前国内外有灾后社区重建的实践和研究资料,提出以地区发展模式为视域是社会工作介入灾后社区重建的有效途径,这主要取决于灾后社区重建的现状和需求以及地区发展模式的本身的特性。地区发展模式是在充分整合地域现有资源的基础上,在一个地域内鼓励居民通过自助及互助来解决社区内的问题,实现共同发展。置于地区发展模式视域下,笔者尝试从服务理念、服务内容、方法和过程三个方面构建社会工作介入灾后社区重建的服务框架。文章最后指出以地区发展模式为视域的社会工作介入灾后社区重建,既是社会工作实务拓展的契机,同时也是实现社会工作职业化的一条重要路径。