中国生猪养殖业规模化影响因素研究

在中国农业产业中,养殖业率先进入规模化发展阶段。基于1998-2011年省际面板数据,运用FGLS法考察生猪养殖规模化的决定因素,发现技术进步、规模经济效益、饲料加工业发育、城乡猪肉消费、交通条件、劳动力非农化、劳动力文化水平以及财政支持政策对规模化具有显著影响。进一步利用回归分解法识别关键因子,结果表明,规模化发展主要取决于四股力量,其中市场拉力是主要的源动力,而交通条件和劳动力文化素质则是重要支撑力,生产扶持政策也形成一定推力,四者的贡献率分别为27%、19%、10%和3%。     

基于完全分解模型的能源消费变动及影响因素分析

在分析Laspeyres指数及其模型不足的基础上,提出更完善、合理的完全分解模型,基于完全分解模型,运用1980~2008年分产业国内生产总值以及能源消费相关统计数据,定量测算并深入分析了能源消费变动及各个影响因素的贡献率、节能量和节能率。研究结果揭示了我国能源消费变动的原因,为进一步研究我国对能源的需求趋势和制定相关的能源政策提供参考。     

股票定价模式及股价分解测度方法研究——基于输入输出转换及相对比较的视角

通过超额收益统计检验研究市场有效性和利用均值-方差投资组合理论间接研究金融资产定价的经典方法与范式正面临尖锐的质疑和挑战.本文从输入输出转换和相对比较的视角对股票定价机制进行了分析,提出了一个涵盖四类定价因素,综合反映股票内在价值和相对价值的定价模式,给出了各组成部分的测度模型.最后,利用9家多重上市公司股票论证了本文提出方法的有效性.     

单向收缩QR算法在奇异值分解中的收敛特性

针对大型矩阵奇异值分解的数值计算问题,总结了单向收缩QR算法的特点,通过实例证明了该算法在处理由某些小幅度信号构造的大型矩阵的奇异值分解时存在不收敛的情况。从理论上分析了QR迭代过程中Givens变换矩阵的变化特点,发现算法出现不收敛现象的根本原因在于大型矩阵首行对角带元素的衰减,最终会使QR迭代时的第一个Givens右矩阵变为单位阵,从而导致后面所有Givens矩阵全部成为单位阵,引起QR算法失效。在此基础上进一步研究了首行元素的衰减对QR算法收敛速度的影响。对理论分析用实际数据进行了验证,从本质上探明了该QR算法的收敛特性。     

Trends of Income Inequality Among the Elderly in Korea

This study investigates the overall trend of inequality among the elderly in Korea and to examine what the most influential factor is for these changes. Although inequality among the elderly is far greater than it is for any other group, little attention has been given to how inequality changes over time. Used are data from the Urban Household Survey with five‐year intervals from 1986 to 2006. The results show that inequality within a cohort increases over time and that earnings and benefits from occupational retirement plans are the most influential factors on overall inequality changes. In addition, the impact of public transfers has gradually increased during the past twenty years. The results imply that our society needs to enact a social policy for lessening earnings inequality in the labor market and to increase public transfers for the elderly.     

Feasible algorithm for linear mixed model for massive data

This article studies computation problem in the context of estimating parameters of linear mixed model for massive data. Our algorithms combine the factored spectrally transformed linear mixed model method with a sequential singular value decomposition calculation algorithm. This combination solves the operation limitation of the method and also makes this algorithm feasible to big dataset, especially when the data has a tall and thin design matrix. Our simulation studies show that our algorithms make the calculation of linear mixed model feasible for massive data on ordinary desktop and have same estimating accuracy with the method based on the whole data.     

职业特征对中国城镇就业人员收入差别的影响(英文)

职业是决定就业人员劳动收入,继而影响居民收入差距程度的重要变量。本文利用国家统计局2005年全国1％人口抽样调查数据中的子样本,对职业与收入差别之间的关系做了经验分析,结果发现职业间收入差距可以解释城镇就业人员收入总体差距的12-17％。造成这种差别的主要原因有二：一是由于各职业对就业人员人力资本上的要求有差异,从而导致了职业间劳动要素报酬上的差异;二是劳动力市场、地区分割所带来的不同职业问人员自由流动的障碍,造成了这种收入差别。前一种原因强调了人力资本的作用,这应当是市场化改革的积极成效;而后一种原因反映的却是现阶段的市场化改革还不彻底。因此,为了缩小职业间不合理的收入差距,我们还应进一步深化改革,尽可能地排除由于市场、地区分割造成的不同职业间人员自由流动的障碍。     

基于Benders分解算法的跨区互联电力系统协调规划模型

研究跨区互联电力系统的协调规划,对于提高投资效率实现更大范围的资源配置具有较强现实意义。本文首先描述多区域电力系统扩张规划问题,并建立多区域扩张规划模型,旨在寻求最优的扩容方案,以最小投入来满足多区域电力系统负荷增长需求;其次,采用Benders分解算法将多区域扩张规划问题分解为一个规划主问题和一个运行子问题,通过主子问题之间的迭代求解,获得最终的最优解;最后,对某个典型的包含7个区域的多区域电力系统进行模拟仿真,验证了本文所构建模型及算法的有效性。     

Restricted maximum likelihood estimation of joint mean‐covariance models

The class of joint mean‐covariance models uses the modified Cholesky decomposition of the within subject covariance matrix in order to arrive to an unconstrained, statistically meaningful reparameterisation. The new parameterisation of the covariance matrix has two sets of parameters that separately describe the variances and correlations. Thus, with the mean or regression parameters, these models have three sets of distinct parameters. In order to alleviate the problem of inefficient estimation and downward bias in the variance estimates, inherent in the maximum likelihood estimation procedure, the usual REML estimation procedure adjusts for the degrees of freedom lost due to the estimation of the mean parameters. Because of the parameterisation of the joint mean covariance models, it is possible to adapt the usual REML procedure in order to estimate the variance (correlation) parameters by taking into account the degrees of freedom lost by the estimation of both the mean and correlation (variance) parameters. To this end, here we propose adjustments to the estimation procedures based on the modified and adjusted profile likelihoods. The methods are illustrated by an application to a real data set and simulation studies. The Canadian Journal of Statistics 40: 225–242; 2012 © 2012 Statistical Society of Canada     

Decomposing the complete graph into dodecahedra

We prove that the complete graph K_v can be decomposed into dodecahedra if and only if v≡ 1, 16, 25 or 40 (mod 60), v≠16.