具有组群异方差结构的面板数据模型及其应用研究

面板数据由不同个体的时间序列数据汇聚而成。已有大量研究表明面板数据个体之间存在组群结构,并且普遍存在模型的异方差现象。本文借鉴组群异质性的研究成果,构建模型误差项组群结构的面板数据模型,基于模型假定条件,提出惩罚伪最大似然函数估计法(PQMLE),该方法能够同时进行结构识别和参数估计;证明了估计量具有Oracle渐近性质;蒙特卡洛模拟验证了该方法有效的样本性质;进一步应用该方法对我国股市进行Fama-French三因子模型的实证分析,验证了理论模型的应用效果。     

测量误差模型稳健方法及应用研究

回归模型在经济学、生物医学、流行病学、工农业生产等众多领域有着广泛的应用,而在实际数据收集时常常出现无法获得变量的精确数据或全部数据的情况,即常碰到测量误差数据、缺失数据等复杂数据情形。对于回归模型中存在测量误差的情况,如在参数估计时不加以修正,则易产生估计偏差,使得估计精度下降。对于数据缺失情形,如不采取合理的处理方法也会导致模型分析结果不佳。故此,本文研究含有测量误差数据时,解释变量具有随机缺失时的线性测量误差模型和部分线性测量误差模型的稳健参数估计问题。本文提出了一种在测量误差服从拉普拉斯分布时参数的损失修正估计,通过蒙特卡洛模拟和医学研究中的实证分析,显示本文所提的估计方法具有偏差小、精度高、稳健性强的优势。     

规模以下工业抽样设计研究

为推动规模以下工业抽样调查工作以及解决当前调查面临的有关问题,本文对抽样设计进行了改进研究。首先,本文对规模以下工业抽样设计演变过程进行系统梳理,总结了现行抽样设计充分利用双重抽样框设计和综合运用三种抽样方法的特点。其次,针对园区层企业密度高的特点,探索结合园区因素改进地域抽样设计,对园区层和非园区层分别抽样,解决调查中面临的非抽样误差问题,并调整辅助变量使其与核心指标相关性均较高,确保抽样推断精度,有效提高抽样调查效率。并以我国东 部某省为例进行实证模拟得到结合园区因素抽样设计对调查工作改进的结论。再次,针对我国各级政府管理需要以及局队业务分工优化调整情况,介绍了规模以下工业样本追加理论和实证应用的主要研究成果。最后,在大数据时代数据来源广泛的背景下,本文在多重抽样框设计以及利用辅助变量提升样本轮换推断精度方面提出了进一步改进抽样设计的思路。     

Understanding Drivers of Risk‐Adjusted Performance for Service Firms with International Operations*

This article investigates whether international operations of service firms increase performance while reducing risk. The article draws on a longitudinal dataset of 584 internationally operating service firms from the United States. Analysis indicates that international diversification is negatively related to risk‐adjusted performance. However, it is established that international diversification interacts with internationalization and positively influences risk‐adjusted performance. This finding offers significant promise for firms, as it indicates that international operations (if managed well), through exposure to varied foreign markets coupled with adequate global scope, can lead to firms’ increased risk‐adjusted performance. The results provide a mechanism for decision‐makers to better understand international operations of service firms and present a strategy for achieving success in international markets by effectively managing two important levers: internationalization and international market diversification.     

Economies of scope in research and teaching: A non-parametric investigation

We propose a non-parametric methodology to study the presence of economies of scope between teaching and research (i.e., the teaching–research nexus). In particular, the paper advocates a conditional version of the ‘benefit-of-the-doubt’ approach to estimate the relationship between professors’ overall academic output, measured by a composite measure of multi-dimensional and importance-adjusted scores of teaching effectiveness and research productivity, and the time devoted to teaching and to research. The methodology is illustrated with a dataset of professors working at a Business & Administration department of a university college where the time allocation of teaching and research was assigned exogenously. The outcome of the analysis indicates the presence of limited scope economies for professors with an extensive research time.     

The Nonverbal Decoding Ability of Children Exposed to Family Violence or Maltreatment: Prospective Evidence from a British Cohort

The prospective association between exposure to family violence or maltreatment in the first four years of life and nonverbal decoding ability at age 8.5 years was examined in a British birth cohort. Overall differences were very minor, except it was found that children exposed to maternal victimization were less accurate in decoding low intensity expressions of fear, than were children from nonviolent homes. Children from violent homes were also more likely to identify expressions of anger, fear, and sadness as happiness. Maltreated children showed a global deficit in decoding emotions, but only when presented as high intensity expressions. Whilst these results point to longitudinal associations between these variables, they do not discount the potential impact of third variables. Results are discussed in relation to current theoretical positions, and the need for further research.     

A comparison of procedures to correct for base-line differences in the analysis of continuous longitudinal data: a case-study

Summary.  The main advantage of longitudinal studies is that they can distinguish changes over time within individuals (longitudinal effects) from differences between subjects at the start of the study (base-line characteristics; cross-sectional effects). Often, especially in observational studies, subjects are very heterogeneous at base-line, and one may want to correct for this, when doing inferences for the longitudinal trends. Three procedures for base-line correction are compared in the context of linear mixed models for continuous longitudinal data. All procedures are illustrated extensively by using data from an experiment which aimed at studying the relationship between the post-operative evolution of the functional status of elderly hip fracture patients and their preoperative neurocognitive status.     

Modelling non-response in the National Child Development Study

Summary.  There is widespread concern that the cumulative effects of the non-response that is bound to affect any long-running longitudinal study will lead to mistaken inferences about change. We focus on the National Child Development Study and show how non-response has accumulated over time. We distinguish between attrition and wave non-response and show how these two kinds of non-response can be related to a set of explanatory variables. We model the discrete time hazard of non-response and also fit a set of multinomial logistic regressions to the probabilities of different kinds of non-response at a particular sweep. We find that the best predictors of non-response at any sweep are generally variables that are measured at the previous sweep but, although non-response is systematic, much of the variation in it remains unexplained by our models. We consider the implications of our results for both design and analysis.     

基于DEA的战略组识别

战略组分析是产业组织理论与战略管理理论中的重要分析工具。但战略组的概念模糊性和战略维度和变量选择以及聚类方法的主观性,使得关于战略组识别存在着矛盾的结论。DEA是适合于明确战略组概念和识别战略组的方法。修正后的DEA,如DEA-Window,特别是最优权多重性问题的解决,能较好地识别战略组。