SELECTION BIAS CORRECTIONS BASED ON THE MULTINOMIAL LOGIT MODEL: MONTE CARLO COMPARISONS

Abstract.  This survey presents the set of methods available in the literature on selection bias correction, when selection is specified as a multinomial logit model. It contrasts the underlying assumptions made by the different methods and shows results from a set of Monte Carlo experiments. We find that, in many cases, the approach initiated by Dubin and MacFadden (1984) as well as the semi-parametric alternative recently proposed by Dahl (2002) are to be preferred to the most commonly used Lee (1983) method. We also find that a restriction imposed in the original Dubin and MacFadden paper can be waived to achieve more robust estimators. Monte Carlo experiments also show that selection bias correction based on the multinomial logit model can provide fairly good correction for the outcome equation, even when the IIA hypothesis is violated.     

试析我国金融资产收益变动对寿险保费的影响

在金融资产选择理论框架下，利用时间序列研究了金融资产长期、短期波动对寿险保费的主要影响。并从居民投资角度建立了寿险与部分金融资产间的ECM模型，结果发现：储蓄增长对保费短期贡献大于长期贡献，加息会在短期内刺激保费增加但长期内有抑制作用；国债和股票受结构性因素影响未表现出与寿险保费有长期均衡关系。寿险公司在短期内应把部分储蓄转化为保费；在长期内应拓展新营销渠道，加快寿险产品和保障型产品的开发。     

建筑市场信息不对称及治理对策研究

本文基于不对称信息理论,建立了委托代理关系下的建筑业信息模型,并具体分析了建筑业目前由于信息不对称造成的各种问题,最后对相关问题提出了几点治理对策和建议。     

Wheat variety yield data: Do commercial and public performance tests provide the same information?

Wheat yields from reported performance test results are of economic importance to wheat producers, since their profits depend on selecting the optimal variety for their location. However, our data shows differences in absolute and relative wheat yields between commercial and public wheat breeding program's performance test data in Kansas. Newly available data are used to test if the difference in yields arose from potential selectivity bias, and to determine the contribution of private and public wheat breeding programs to varietal yield improvement during 2007–2012. Both Heckman selection models and multiple regression showed no statistical evidence of the potential presence of selectivity bias rather, managerial practices, agronomic conditions, field location, and inherent genetic traits of the seed variety were identify as the source of yield differences.     

Objective methods for graphical structural learning

Graphical models are used for expressing conditional independence relationships among variables by the means of graphs, whose structure is typically unknown and must be inferred by the data at hand. We propose a theoretically sound Objective Bayes procedure for graphical model selection. Our method is based on the Expected-Posterior Prior and on the Power-Expected-Posterior Prior. We use as input of the proposed methodology a default improper prior and suggest computationally efficient approximations of Bayes factors and posterior odds. In a variety of simulated scenarios with varying number of nodes and sample sizes, we show that our method is highly competitive with, or better than, current benchmarks. We also discuss an application to protein-signaling data, which wieldy confirms existing results in the scientific literature.     

Assessing self-selection and endogeneity issues in the relation between activity-based costing and performance

Studies investigating the relation between ABC adoption and performance are inconclusive and plagued with econometric problems. This study extends prior research to investigate the association between ABC adoption and four manufacturing plant performance measures (cycle-time improvement, quality improvement, cost improvement, and profitability) and to assess selection bias and the endogenous nature of their relationship. I use the Heckman (1979) model to assess sample selection bias and the Wooldridge (2002) 2SLS-IV approach, to investigate endogeneity. After controlling for sample selection bias and endogeneity, the coefficient of ABC under the Heckman method and ABC_fit under the 2SLS-IV method becomes significantly higher compared to the coefficient of ABC under the OLS method. In addition, both the inverse Mills ratio, under the Heckman model, and Hausman F-test, under the Wooldridge 2SLS approach, are positive and significant, confirming the presence of both sample selection bias and endogeneity. Overall, I find that controlling for sample selection bias and endogeneity is essential in properly assessing the significance of ABC-performance association.     

Relationship between city size and firm productivity – A new interpretation using the Chinese experience

This paper contributes to the literature on the relationship between city size and firm productivity by focusing on agglomeration, selection (market competition), and sorting (presence of firms with diverse productivity) effects using Chinese firm-level data for 1998–2013. Contrary to the existing literature, our parametric regression estimates from nearly two million firms show that when the selection effect is controlled, productivity advantage in big cities is reversed. This outcome is explained through a quantile regression showing the existence of left-sided sorting (inefficient firms sort themselves to larger cities) in big cities which is not captured in existing empirical literature. We further find that (1) left-sided sorting is stronger in exporters than non-exporters; (2) is also generated mainly in enterprises with high asset-liability ratios; and (3) selection has a positive effect on firm productivity, suggesting that market competition is key in an explanation of the rapid growth of big cities in China.     

石衡沧港城际铁路互联互通方案研究

突出功能定位,发挥路网互联互通作用,是高速铁路互联互通方案研究的关键。在阐述石衡沧港城际铁路互联互通现状的基础上,针对石衡沧港城际铁路客流特点和功能定位,分析石衡沧港城际铁路石家庄铁路枢纽、衡水铁路枢纽、沧州铁路枢纽和黄骅铁路枢纽等互联互通主要节点枢纽,通过衡水、沧州和黄骅铁路枢纽比选方案分析,提出石衡沧港城际铁路在通道中的枢纽方案,为区域连接线、城际铁路在方案互联互通作用提供研究支撑。     

Why do some consumers shop in this pharmacy? A cross-check of vulnerable characteristics and store types

Research on vulnerable consumers remains unfailing in macromarketing and social marketing. Yet it is unclear how to operationalize the vulnerable consumers by demographics and further to this it is rarely touched how the vulnerable consumers defined by different measures make decision when choosing the place to shop especially in pharmacy retailing sector. The authors conduct a comparative study of variously-defined vulnerable consumers for their shopping store types in an urban Chinese city to investigate how people with distinct backgrounds develop their decision making rules and choose different types of retail pharmacies. This paper casts light on customer heterogeneity associated with different dimensions of vulnerability by using consumer demographics, and indicates that four dimensions of vulnerability exist as cognitive capability, social relations, behaviors, and the institutional protection in health-related sector. These four aspects of vulnerability play a significant role in identifying different shop selection patterns. Findings suggest that efforts to boost store patronage targeting on various consumer groups should have different strategies to reach consumers’ mindsets.     

基于系统动力学的中小企业云计算服务商选择风险分析

全面的认识和评估风险是做出正确决策的关键基础。本文对中小企业云计算服务商选择风险进行全面分析，将风险分为机会成本、信息不对称、逆向选择、连锁风险以及冲突风险五个方面，并建立系统动力学模型，进行仿真，最后得出中小企业云计算服务商选择风险发展趋势并对趋势进行分析。