流动人口的社会阶层、社会流动与未婚先孕——以上海市为例

采用二元逻辑斯蒂回归模型,从社会阶层与社会流动的视角对影响流动人口未婚先孕的因素进行分析.关于社会阶层的研究结果显示,育龄妇女的受教育程度与月均收入水平两因素的影响结果显著,受教育程度越高未婚先孕的比例越低,收入越高未婚先孕的比例越低.育龄妇女的户口对未婚先孕不产生显著性影响;关于社会流动的研究结果显示,育龄妇女婚姻的教育匹配与户口匹配对未婚先孕有着显著性影响,教育匹配的上向流动增加未婚先孕的比例,下向流动降低未婚先孕的比例.但户口匹配却显示出上向流动降低未婚先孕的比例,下向流动增加未婚先孕的比例.     

Productivity,efficiency, and non-performing loans in the Chinese banking industry

In this paper, the directional distance function and the metafrontier-Luenberger productivity indicator are used to measure the efficiency and the total factor productivity in 25 Chinese commercial banks over the period between 2004 and 2010. It is found that the pure technical efficiency of the state-owned commercial banks is better than that of the joint-stock commercial banks and the city commercial banks, while non-interest income is the major source of inefficiency. In total, the Chinese banking industry performs well in terms of overall productivity. The technological scale change indicating the change of return to scale in technology is the driving force for overall productivity growth. However, the pure technical efficiency change and the pure technologic change are not significant, and the scale efficiency change has a negative effect to productivity. The potential technological relative change for the three groups is greater than zero.     

从“官吏分途”到“层级分流”:帝国逻辑下的中国官僚人事制度

魏晋南北朝以来的“官吏分途”是中国官僚体制的重大制度变迁,本文从这一角度出发,审视当代中国官员的空间流动状况,提出以“官吏相对谱系”为特点的“层级分流”模式。文章从周雪光的“帝国逻辑”分析框架出发,借用史学研究和社会科学理论来认识和解释人事制度安排与帝国治理逻辑之间的关系。文章认为,从“官吏分途”到“层级分流”,这一人事制度造成了官僚体制的二元结构及其迥然不同的职业生涯、激励设置和利益群体,为中国官僚体制的运作打上了鲜明烙印。本文充实和扩展了“帝国逻辑”的理论思路。     

FDI进入方式与企业生产率——非参数分析方法

采用1998-2007年中国制造业外商投资企业的非平衡面板数据,在估计企业全要素生产率的基础上,采用一阶随机占优方法比较分析了外商独资企业与中外合资企业全要素生产率的差异。研究发现,中国外商独资企业的生产率在总体上并不比中外合资企业高,但随着跨国公司母国与中国制度特别是经济制度的差距逐渐缩小,外商独资企业的生产率不断提高;随着FDI进入时间的推移,外商独资企业逐渐克服进入初期的不利因素,其生产率明显高于中外合资企业;大中型中外合资企业可能由于能较好地适应中国的文化、管理特点以及经营协同效应的存在,其生产率明显高于大中型外商独资企业。     

A Bayesian estimation of lag lengths in distributed lag models

Dynamic regression models are widely used because they express and model the behaviour of a system over time. In this article, two dynamic regression models, the distributed lag (DL) model and the autoregressive distributed lag model, are evaluated focusing on their lag lengths. From a classical statistics point of view, there are various methods to determine the number of lags, but none of them are the best in all situations. This is a serious issue since wrong choices will provide bad estimates for the effects of the regressors on the response variable. We present an alternative for the aforementioned problems by considering a Bayesian approach. The posterior distributions of the numbers of lags are derived under an improper prior for the model parameters. The fractional Bayes factor technique [A. O'Hagan, Fractional Bayes factors for model comparison (with discussion), J. R. Statist. Soc. B 57 (1995), pp. 99–138] is used to handle the indeterminacy in the likelihood function caused by the improper prior. The zero-one loss function is used to penalize wrong decisions. A naive method using the specified maximum number of DLs is also presented. The proposed and the naive methods are verified using simulation data. The results are promising for the method we proposed. An illustrative example with a real data set is provided.     

Full information maximum likelihood estimation in factor analysis with a large number of missing values

We consider the problem of full information maximum likelihood (FIML) estimation in factor analysis when a majority of the data values are missing. The expectation–maximization (EM) algorithm is often used to find the FIML estimates, in which the missing values on manifest variables are included in complete data. However, the ordinary EM algorithm has an extremely high computational cost. In this paper, we propose a new algorithm that is based on the EM algorithm but that efficiently computes the FIML estimates. A significant improvement in the computational speed is realized by not treating the missing values on manifest variables as a part of complete data. When there are many missing data values, it is not clear if the FIML procedure can achieve good estimation accuracy. In order to investigate this, we conduct Monte Carlo simulations under a wide variety of sample sizes.     

A pooled Bayes test of independence for sparse contingency tables from small areas

We study the association between bone mineral density (BMD) and body mass index (BMI) when contingency tables are constructed from the several U.S. counties, where BMD has three levels (normal, osteopenia and osteoporosis) and BMI has four levels (underweight, normal, overweight and obese). We use the Bayes factor (posterior odds divided by prior odds or equivalently the ratio of the marginal likelihoods) to construct the new test. Like the chi-squared test and Fisher's exact test, we have a direct Bayes test which is a standard test using data from each county. In our main contribution, for each county techniques of small area estimation are used to borrow strength across counties and a pooled test of independence of BMD and BMI is obtained using a hierarchical Bayesian model. Our pooled Bayes test is computed by performing a Monte Carlo integration using random samples rather than Gibbs samples. We have seen important differences among the pooled Bayes test, direct Bayes test and the Cressie-Read test that allows for some degree of sparseness, when the degree of evidence against independence is studied. As expected, we also found that the direct Bayes test is sensitive to the prior specifications but the pooled Bayes test is not so sensitive. Moreover, the pooled Bayes test has competitive power properties, and it is superior when the cell counts are small to moderate.     

Bayesian compartmental model for an infectious disease with dynamic states of infection

Population-level proportions of individuals that fall at different points in the spectrum [of disease severity], from asymptomatic infection to severe disease, are often difficult to observe, but estimating these quantities can provide information about the nature and severity of the disease in a particular population. Logistic and multinomial regression techniques are often applied to infectious disease modeling of large populations and are suited to identifying variables associated with a particular disease or disease state. However, they are less appropriate for estimating infection state prevalence over time because they do not naturally accommodate known disease dynamics like duration of time an individual is infectious, heterogeneity in the risk of acquiring infection, and patterns of seasonality. We propose a Bayesian compartmental model to estimate latent infection state prevalence over time that easily incorporates known disease dynamics. We demonstrate how and why a stochastic compartmental model is a better approach for determining infection state proportions than multinomial regression is by using a novel method for estimating Bayes factors for models with high-dimensional parameter spaces. We provide an example using visceral leishmaniasis in Brazil and present an empirically-adjusted reproductive number for the infection.     

Error variance bias in neighbour balance and evenness of distribution designs

Neighbour balance and evenness of distribution designs help to address user concerns in the two‐dimensional layout of agricultural field trials. This is done by minimising the occurrence of pairwise treatment plot neighbours and ensuring that the replications of treatments are spread out across rows and columns of a trial. Such considerations result in a restriction on the normal randomisation process for a row‐column design which can lead to error variance bias. In this paper, uniformity trial data is used to assess the degree of this bias for both resolvable and non‐resolvable designs. Comparisons are made with a similar investigation using Linear Variance spatial designs.     

Estimation of factor-augmented panel regressions with weakly influential factors

The use of factor-augmented panel regressions has become very popular in recent years. Existing methods for such regressions require that the common factors are strong, an assumption that is likely to be mistaken in practice. Motivated by this, the current article offers an analysis of the effect of weak, semi-weak, and semi-strong factors on two of the most popular estimators for factor-augmented regressions, namely, principal components (PC) and common correlated effects (CCE).