中国能源消费水平空间差异及成因研究

本文运用离差指标来测度中国能源消费水平空间差异,并将离差平方之和分解为地区内差异和地区间差异,使得能够测算总体差异的地区构成;将离差绝对值之和分解为各影响因素贡献份额,使得能够找出影响地区差异的主要影响因素。研究结果表明中国能源消费水平空间差异不断扩大;能源消费水平总体差异主要是由三大地区内部差异引起的,其中地区内部差异主要来自于东部地区;人均资本存量是影响我国能源消费水平空间差异的主要因素。本文据此提出相应的政策建议。     

论全球化语境下美国戏剧文学的发展

美国戏剧文学是在欧洲戏剧文学传统的影响下,在以政治剧为起点、以本民族的"人学"为己任、把"小人物"搬上舞台、对社会及人类自身进行批判的过程中发展起来的。然而,美国戏剧文学的发展之路也曾遭遇了大众消费价值与文艺思想价值之间的冲突;在现今阶段又受到后现代思潮的冲击,传统意义上的戏剧文学几乎在性质上被彻底颠覆。秘鲁诺贝尔文学奖作家略萨为当代美国戏剧文学走出困境做出了榜样。     

"员工流动成长效应":结构模型构建与实证分析

本文分析了"员工流动成长效应",通过访谈和问卷调查获得数据,采用项目分析、探索性因子分析以及验证性因子分析等方法,构建和检验了"员工流动成长效应"的结构模型。研究表明,"员工流动成长效应"是个并列的七因子构念,这七个因子包括发展空间、创新能力、社会能力、职业能力、自我认知、工作业绩和报酬水平。文章通过ANOVA差异分析检验了主动流动与被动流动两种流动类型"员工流动成长效应"的差异。结果表明,主动流动与被动流动在发展空间、社会能力、职业能力、工作业绩以及报酬水平五个方面存在显著差异,而在创新能力、自我认知两个方面的差异则不显著。     

一类近似因子模型的GMM估计及其统计性质研究

对于一类异质性误差项存在截面相关性的近似因子模型,本文首先提出了估计共同因子向量和因子载荷矩阵的广义矩估计方法（GMM）,该方法推广了Doz等（2012）的极大似然估计方法;其次,分别研究了模型参数广义矩估计的渐近性质和有限样本的统计性质,在适当的条件下,证明了参数的GMM估计是具有渐近正态分布的一致估计;最后,利用近似因子模型对我国各类上市公司增长性的共同驱动因素及其差异性进行了实证分析。     

中国出口产品质量提高了吗

本文基于Khandelwal(2010)的出口产品质量测度思路及Berry（1994）的嵌套Logit模型,构建了测度中国出口产品质量的理论框架。测度结果表明：我国制造业总体的质量水平呈缓慢上升趋势,但各行业表现出不同的特征。在此基础上,对我国出口产品质量决定因素进行了多维度的经验考察,得到了以下基本结论：我国人均国民收入较高时,它与出口产品质量显著正相关;随着一般贸易份额的增加,其对出口质量的提升已超过了加工贸易;企业研发对劳动密集型出口产品质量贡献最大,对资本密集型产品质量贡献最小;人力资本对出口产品质量的贡献刚好跟国内研发相反;外资出资方式对出口产品质量影响与其采取的贸易方式有关。另外,企业中间品投入、资本强度及政府的研发补贴都会对出口质量产生影响。据此,本文认为在引资导向上应逐步引导外资与一般贸易方式的结合力度;适度加大对传统劳动密集型行业的研发力度是促进产业结构优化升级的重要途径;需加强企业中间投入品的投入,优化要素投入比例,积极培育高质量、适合各行业实际发展需要的人力资本。     

稳健因子分析方法的构建及比较研究

由于传统因子分析方法对离群值较敏感,导致计算结果与实际不相符。针对这一现象,本文运用FAST-MCD方法对传统因子分析方法进行改进,构建出因子分析的稳健算法,以克服离群值的影响,并对此方法进行了模拟和实证分析。模拟和实证分析结果均表明：因子旋转前后,当数据中不存在离群值时,传统因子分析与稳健因子分析得到的结果基本保持一致;当数据中存在离群值时,运用传统因子分析得到的结果出现较大变化,而运用稳健因子分析方法得到的结果基本不变,这说明相对于传统因子分析方法,稳健因子分析方法能有效抵抗离群值的影响,具有良好的抗干扰性和高抗差性。     

Test for Generalized Variance in Factor Analysis Model

We derive a likelihood ratio test for generalized variance a in factor analysis model. The asymptotic distribution of the test statistic follows chi-square distribution with one degree of freedom from a general theory of likelihood ratio test.     

Generalized Linear Factor Models: A New Local EM Estimation Algorithm

In this article, a general approach to latent variable models based on an underlying generalized linear model (GLM) with factor analysis observation process is introduced. We call these models Generalized Linear Factor Models (GLFM). The observations are produced from a general model framework that involves observed and latent variables that are assumed to be distributed in the exponential family. More specifically, we concentrate on situations where the observed variables are both discretely measured (e.g., binomial, Poisson) and continuously distributed (e.g., gamma). The common latent factors are assumed to be independent with a standard multivariate normal distribution. Practical details of training such models with a new local expectation-maximization (EM) algorithm, which can be considered as a generalized EM-type algorithm, are also discussed. In conjunction with an approximated version of the Fisher score algorithm (FSA), we show how to calculate maximum likelihood estimates of the model parameters, and to yield inferences about the unobservable path of the common factors. The methodology is illustrated by an extensive Monte Carlo simulation study and the results show promising performance.     

A Note on Equality and Inequality of Some Factor Score Predictors

Anderson and Rubin (1956), as well as Takeuchi et al. (1982) finally Schneeweiss and Mathes (1995) proposed factor score predictors that were regarded as orthogonal. Anderson and Rubin's and Takeuchi et al.'s factor score predictors are shown to be identical for non zero unique variances, although they have never been claimed being identical. It is shown that the Schneeweiss and Mathe's factor score predictor is not equal to McDonald's factor score predictor, although it has been claimed that these predictors are identical. It is, moreover, shown that the Schneeweiss and Mathe's factor score predictor is orthogonal only for the canonical orthogonal factor model.     

Variance Inflation Factor and Condition Number in multiple linear regression

The Variance Inflation Factor and the Condition Number are measures traditionally applied to detect the presence of collinearity in a multiple linear model. This paper presents the relation and the difference between both measures from theoretical and empirical perspectives by using Monte Carlo simulations and taking special interest in the computational techniques.