中国农村居民收入差距的分位数回归解析

通过对1997～2009年中国农村居民收入差距进行分位数回归发现:工资性收入的增长是农村居民收入差距扩大的最主要原因,而财产性收入以及转移性收入则发挥着缩小农村居民收入差距的作用,家庭经营收入对收入差距的影响较小。出现这种结果的原因在于农民工流动的不稳定性导致农村居民家庭收入构成出现较大的波动,从而导致这一时期农村居民收入差距波动。     

基于分位回归法的农民工收入影响因素分析

 理论界对影响农民工收入水平的研究,主要是从总体上分析影响收入的各种因素所起的作用及其它们之间的相互关系。本文利用分位回归模型对抽样调查所获得的数据进行处理,对影响因素的各分位数分析,更为细致和深入地研究农民工收入及其影响因素之间的回归关系。通过分位回归分析,分别从农民工自身、社会相关管理部门和用人单位的角度出发,对提高农民工的收入水平提出相应的建议。     

基于分位数分解的城乡收入差距研究

文章基于中国家庭金融调查(CHFS)的调查数据,分别利用分位数回归和分布函数分解的方法,检验了城乡居民收入水平的主要影响因素,分解比较城乡收入差距中城乡居民禀赋特征构成差异和个体特征回报率差异的相对贡献.根据实证结果可以看到,受教育程度、职业性质等对城乡居民收入有显著影响,禀赋特征构成差异和个体特征回报率差异都扩大了城乡居民收入,其中城乡居民禀赋特征构成差异的影响更大.     

中国城乡教育支出差距对城乡收入差距的影响

本文在建立向量自回归模型的基础上,运用脉冲响应函数和预测方差分解研究中国城乡教育支出差距对城乡收入差距的动态影响。研究结论表明:只有长期增加农村教育的投入,提高整个社会尤其是农村的平均教育水平,最终通过教育的平等化,才能达到缩小城乡收入差距的目的。此外,从长期来看,城乡教育支出差距对城乡收入差距波动的影响程度大约为16%,这说明要从根本上缩小城乡收入差距,除了教育之外,还要许多其它的工作要做。     

各级教育投入、劳动力转移与城乡居民收入差距

本文从劳动力转移视角出发研究各级教育投入对城乡收入差距影响的微观机制,并探讨新常态下,如何进一步提高教育经费资源的配置效率。文章通过构建含二元经济结构特征的一般均衡模型,利用1995-2014年省级数据与动态空间面板模型对各级生均教育经费投入、劳动力转移与城乡收入差距的作用机制进行理论分析和实证检验。结果显示：一方面,教育投入是缓解我国城乡收入差距,实现城乡帕累托改进的有效手段,其对城乡收入差距的影响同时具有直接效应与间接效应。另一方面,各级教育投入效果不一,相比而言,义务教育尤其是初中阶段教育作用更加显著。最后,在我国宏观经济减速调整的背景下,加大教育经费投入不仅可在短期弥补私人投资减少平滑经济增长,还可促进人力资本积累提高经济潜在增速。教育投入再分配带来的劳动力转移既减少了城乡收入差距也有利于缓解就业结构转型滞后的矛盾,是实现兼具公平的包容性增长目标的重要保障。     

运用分位回归特征价格模型构建住房价格指数

文章采用上海市新建住房及二手住房交易数据,在特征价格模型的基础上,运用分位回归编制住房价格指数,并通过与OLS回归结果对比,验证其必要性及可行性。结果发现,不同层次的住房价格波动存在显著差异,房价上涨率从低端住房向高端住房递减,低分位点的房价指数波动更大。     

基于分位回归的风险保费预测

风险保费预测是非寿险费率厘定的重要组成部分。在传统的分位回归厘定风险保费中,通常假设分位数水平是事先给定的,缺乏一定的客观性。为此,提出了一种应用分位回归厘定风险保费的新方法。基于破产概率确定保单组合的总风险保费,建立个体保单的分位回归模型,并与总风险保费建立等式关系,通过数值方法求解出分位数水平,实现对个体保单风险保费的预测。通过一组实际数据分析表明,该方法具有良好的预测效果。     

高管受教育程度与收入差距关系的实证分析

文章以我国A股上市公司为例,选取2003-2014年的数据,研究了高管受教育程度与其收入差距的关系.研究表明,企业高管的受教育程度对其薪酬有正向作用,能够拉大高管之间的收入差距,但高管职务及其金融背景却会缩小这种收入差距.进一步研究表明,相对于非国有企业,国有企业中高管的教育程度对收入差距的影响更大;而且相对于地方国企,中央国企的这种效应也更为显著.     

样本选择参数分位回归模型及其在工资分布分解中的应用

在工资差距分解问题中,研究者经常会遇到样本选择偏差问题,直接忽略会导致最终估计结果产生严重偏差,同时在众多工资差距分解方法中,相比于均值分解,分布分解方法更受研究者青睐。针对参数分位回归,本文首次提出可加形式与非可加形式的样本选择参数分位回归（SSPQR）模型,并基于这两类样本选择参数分位回归模型给出修正样本选择偏差后的参数分位回归工资差距分布分解方法。运用上述方法及已有的工资分布分解方法,借助CHNS2015年度城镇数据,本文研究了我国城镇男女工资差距及差距分解问题,得出以下结论：①男女工资差距主要来源是性别歧视问题;②经过样本选择偏差修正后,实际的工资差距更大,歧视问题更严重;③男女工资差距程度在不同分位点上结果不同,换句话说,我们不能简单地仅从平均水平来判断工资差距程度;④与其他已有方法计算结果比较发现,SSPQR计算的工资差距程度更大。     

二氧化碳排放与经济增长——基于分位回归验证Kuznets假说

文章运用分位回归方法探讨二氧化碳排放与经济增长之间的关系。分位回归有助于解释在不同分位数下因变量与自变量之间关系。结果表明：二氧化碳排放与经济增长的关系总体呈“倒U型”,但在不同阶段会呈现“N型“。二氧化碳排放高的地区存在着比较明显EKC曲线趋势,也就是说,随着经济水平提高,二氧化碳排放将逐渐减少,但目前我国还处于上升时期。     

Linear Quantile Regression Based on EM Algorithm

This article aims to put forward a new method to solve the linear quantile regression problems based on EM algorithm using a location-scale mixture of the asymmetric Laplace error distribution. A closed form of the estimator of the unknown parameter vector β based on EM algorithm, is obtained. In addition, some simulations are conducted to illustrate the performance of the proposed method. Simulation results demonstrate that the proposed algorithm performs well. Finally, the classical Engel data is fitted and the Bootstrap confidence intervals for estimators are provided.     

Influence Measures in Quantile Regression Models

In this article, we use the asymmetric Laplace distribution to define a new method to determine the influence of a certain observation in the fit of quantile regression models. Our measure is based on the likelihood displacement function and we propose two types of measures in order to determine influential observations in a set of conditional quantiles conjointly or in each conditional quantile of interest. We verify the validity of our average measure in a simulated data set as well in an illustrative example with data about air pollution.     

分量回归下的中国股市价量关系研究

本文用分量回归的方法来分析中国股市收益率和成交量关系。实证结果发现中国股市具有“价量齐扬”和“价跌量缩”的现象,但前者在接近最大涨幅时减弱,而后者在接近最大跌幅时增强。然若采用传统的OLS方法分析,则无法发现这种不对称性。对于此涨跌幅下的价量关系不对称特征,我们认为可能的原因是股市的卖空限制使投资人无法对市场信息（尤其是负面信息）充分反应,因此造成正负收益率与成交量之间的不对称关系。     

Confidence Corridors for Multivariate Generalized Quantile Regression

We focus on the construction of confidence corridors for multivariate nonparametric generalized quantile regression functions. This construction is based on asymptotic results for the maximal deviation between a suitable nonparametric estimator and the true function of interest, which follow after a series of approximation steps including a Bahadur representation, a new strong approximation theorem, and exponential tail inequalities for Gaussian random fields. As a byproduct we also obtain multivariate confidence corridors for the regression function in the classical mean regression. To deal with the problem of slowly decreasing error in coverage probability of the asymptotic confidence corridors, which results in meager coverage for small sample sizes, a simple bootstrap procedure is designed based on the leading term of the Bahadur representation. The finite-sample properties of both procedures are investigated by means of a simulation study and it is demonstrated that the bootstrap procedure considerably outperforms the asymptotic bands in terms of coverage accuracy. Finally, the bootstrap confidence corridors are used to study the efficacy of the National Supported Work Demonstration, which is a randomized employment enhancement program launched in the 1970s. This article has supplementary materials online.     

Non-iterative Estimation and Variable Selection in the Single-index Quantile Regression Model

A new estimation procedure is proposed for the single-index quantile regression model. Compared to existing work, this approach is non-iterative and hence, computationally efficient. The proposed method not only estimates the index parameter and the link function but also selects variables simultaneously. The performance of the variable selection is enhanced by a fully adaptive penalty function motivated by the sliced inverse regression technique. Finite sample performance is studied through a simulation study that compares the proposed method with existing work under several criteria. A data analysis is given that highlights the usefulness of the proposed methodology.     

Focused Information Criterion and Model Averaging in Quantile Regression

In this article, we study model selection and model averaging in quantile regression. Under general conditions, we develop a focused information criterion and a frequentist model average estimator for the parameters in quantile regression model, and examine their theoretical properties. The new procedures provide a robust alternative to the least squares method or likelihood method, and a major advantage of the proposed procedures is that when the variance of random error is infinite, the proposed procedure works beautifully while the least squares method breaks down. A simulation study and a real data example are presented to show that the proposed method performs well with a finite sample and is easy to use in practice.     

Nonparametric Testing of an Exclusion Restriction in Quantile Regression

Using the framework proposed by Bickel et al. (2006 Bickel , P. J. , Ritov , Y. , Stoker , T. ( 2006 ). Tailor-made tests for goodness-of-fit to semiparametric hypotheses . Ann. Stat. 34 ( 2 ): 721 – 741 . [Google Scholar]), we provide a score-based testing method to check the exclusion restriction in quantile regression, i.e., H: ν_α(Y|U, V) = ν_α(Y|U) w.p.1, where ν_α denotes the αth (0 < α < 1) quantile. A subsampling method is suggested to acquire the critical values and justified. The tests are all found to be consistent against fixed alternatives and have discriminating power against local alternatives at root-n scale. We address this particular problem as a representative among a wide family of semiparametric model checking problems. The methodology can be carried over to other goodness-of-fit testing of semiparametric models, possibly involve non smooth functions.     

Quantile Regression For Longitudinal Biomarker Data Subject to Left Censoring and Dropouts

Quantile regression is increasingly used in biomarker analysis to handle nonnormal or heteroscedastic data. However, in some biomedical studies, the biomarker data can be censored by detection limits of the bioassay or missing when the subjects drop out from the study. Inappropriate handling of these two issues leads to biased estimation results. We consider the censored quantile regression approach to account for the censoring data and apply the inverse weighting technique to adjust for dropouts. In particular, we develop a weighted estimating equation for censored quantile regression, where an individual’s contribution is weighted by the inverse probability of dropout at the given occasion. We conduct simulation studies to evaluate the properties of the proposed estimators and demonstrate our method with a real data set from Genetic and Inflammatory Marker of Sepsis (GenIMS) study.     

工资收入差异的解释：基于分位数回归的经验研究

利用CHNS2006年的数据,通过分位数回归方法从教育回报率、性别和工作部门的差异三个方面对中国工资收入差异进行研究,得出与以往研究不同的结论。结果表明：教育回报率在工资收入分布上的变动趋势是不定的。在工资收入分布的两端,大专以上学历对工资收入差距的影响相对较大。对不同性别间工资收入差异的分解表明劳动力市场上存在明显的性别歧视,而对部门间工资差异的分解表明在整个工资分布区间,这种差异呈倒＂U＂型走势。