SUCCESSIVE MEASUREMENT EXPERIMENTS

Abstract. We consider methods for the analysis of successive measurements, with emphasis on practical usefulness. It is described how the methods can be applied by using common techniques like regression analysis and analysis of variance.     

我国通货膨胀的国际影响因素分析——基于结构向量自回归模型的实证研究

全球金融危机爆发以来,美元持续贬值引起国际原材料价格上涨和国际资本流动扩大.在全球流动性泛滥的背景下,我国通货膨胀屡创新高.文章从美元贬值导致的国际原材料价格波动、国内外利率因素、人民币预期升值三个角度,分别结合国内经济增长,探讨了国际因素对我国通货膨胀的影响.研究发现,国内经济的过热增长是我国通货膨胀的主导因素,但外部冲击特别是国际原油价格对我国通货膨胀的影响也不容忽视.我国不完善的汇率和利率机制,推动了外部因素对我国通货膨胀的冲击,国际因素对我国工业领域通货膨胀的影响相对消费领域而言偏高.     

Bonds versus stocks: Investors’ age and risk taking

It has become increasingly popular to advise investors to relocate their funds from a primarily stock portfolio to a primarily bond portfolio as they get older. However, the well-known decision rules such as mean–variance or stochastic dominance rules are unable to explain this common practice. Almost stochastic dominance (ASD) and almost mean–variance (AMV) approaches are used to examine the dominance of stock and bond portfolios. ASD and AMV rules unambiguously support the popular practice of advising higher stock to bond ratio for long investment horizons. Hence, we provide an explanation to the practitioners’ recommendation within the expected utility paradigm.     

Optimal Allocation for Comparing <Emphasis Type="Italic">k</Emphasis> Test Treatments to Positive and Negative Control with Unequal Weighting Under A-optimality and MV-optimality

Experiments in real life often involve comparisons of test treatments to more than one control. However, the controls may not always be of equal importance. In this paper we introduce weighted MV optimality criterion and present a detailed study using both weighted A and MV optimality criteria, of the problem of optimally comparing a set of test treatments to two controls (positive and a negative) that are of unequal importance to the experimenter.     

对普适性生产函数模型的一些改进

普适性生产函数方法为使用横截面数据估计时,由于各地区生产函数的不同所导致的不可估算问题,提供了很好地解决办法,但其参数的估计需用差分模型,这将产生严重的缺陷.文章放宽其基本假设,得到更一般的可估计模型——异方差模型,经验证据亦表明,改进后的模型优于原有模型.     

The effect of CEOs on firm performance

The extent to which CEOs influence firm performance is fundamental to scholarly understanding of how organizations work; yet, this linkage is poorly understood. Previous empirical efforts to examine the link between CEOs and firm performance using variance decomposition, while provocative, nevertheless suffer from methodological problems that systematically understate the relative impact of CEOs on firm performance compared to industry and firm effects. This study addresses these methodological problems and reexamines the percentage of the variance in firm performance explained by heterogeneity in CEOs. The results of this study suggest that in certain settings the ‘CEO effect’ on corporate‐parent performance is substantially more important than that of industry and firm effects, but only moderately more important than industry and firm effects on business‐segment performance. Copyright © 2008 John Wiley & Sons, Ltd.     

Decomposing Income Inequality and Policy Implications in Rural China

Using village data from samples covering 6 provinces,36 counties and 216 townships,the income inequalities within and between townships in rural China are assessed. The Theil index and the mean logarithmic deviation methods enable us to test income inequality at the township level,and to decompose it into intra-regional and inter-regional at county and provincial levels. In the present paper,we also decompose income inequalities between and within the nationally designated poor counties (NDPC). The results show that approximately two-thirds of the income inequality in rural China would be eliminated if measures and policies were targeted at the county level. This study also confirms the rationale that China's poverty alleviation strategy of focusing on poor counties based on the inequalities between NDPC and non-NDPC accounts for the most inter-province inequality.     

BQ分解在核心通货膨胀中的应用研究

文章对Blanchard and Quah趋势分解（BQ分解）在核心通货膨胀中的应用进行了深入的研究,并针对其在应用中所存在的问题提出相应的解决方案。 BQ分解是根据菲利普斯曲线理论发展而来的,主要用于对多维变量的趋势分解。研究表明,两维var模型的BQ分解通常是充分可解的。但是多维BQ分解由于自身的结构性原因,并不能保证一定可解出有意义的实数解。文章也证明了文献中所提出为了解决该问题的Cholesky分解,其与BQ分解相互矛盾而不可采用,所以文章推荐采用校准的方法。实证表明,由校准BQ分解所得到的核心通货膨胀完全满足理论和实践对它的要求,能够预测CPI指数的发展趋势,所以作为解决多维BQ分解无法正常求解时的备选方法,校准是一种便捷而有效的方法。     

中国 R & D 强度区位分布条件因素的差异分析--基于稳健MM估计的EBA模型的实证研究

依据空间计量经济学的相关理论,运用稳健MM估计的EBA （异常值检验的极值边界分析）模型,采用中国30个省际区域2002～2012年的面板数据,实证研究中国东部、中部、西部地区R&D强度区位分布条件的“稳健性（Robust ）”影响因素。结果表明：我国东部、中部、西部各地区的R&D强度存在差异,且其影响因素也不尽相同。R&D强度较高的东部地区,科技水平、市场规模、固定资产投资、要素禀赋等4个因素对中国R&D强度具有抗干扰的“稳健性”影响;R&D强度中等的中部地区,3个“稳健性”影响因素是政府公共政策、科技水平和要素禀赋;而对于R&D强度较低的西部地区,技术创新和要素禀赋对提高R&D强度作用具有“稳健性”。由此揭示我国R&D强度的发展规律以及各区域间的差异性,并根据实证结论提出一些政策建议,为各地区制定科技政策目标和实施方案提供经验证据和决策参考。