How are journal impact,prestige and article influence related? An application to neuroscience

The paper analyzes the leading journals in neurosciences using quantifiable research assessment measures (RAM), highlights the similarities and differences in alternative RAM, shows that several RAM capture similar performance characteristics of highly cited journals, and shows that some other RAM have low correlations with each other, and hence add significant informational value. Alternative RAM are discussed for the Thomson Reuters ISI Web of Science database (hereafter ISI). The RAM that are calculated annually or updated daily include the classic 2-year impact factor (2YIF), 5-year impact factor, immediacy (or zero-year impact factor), Eigenfactor score, article influence score, C3PO (citation performance per paper online), h-index, Zinfluence, PI-BETA (papers ignored by even the authors), 2-year and historical self-citation threshold approval ratings, impact factor inflation, and cited article influence (CAI). The RAM are analyzed for 26 highly cited journals in the ISI category of neurosciences. The paper finds that the Eigenfactor score and PI-BETA are not highly correlated with the other RAM scores, so that they convey additional information regarding journal rankings, that article influence is highly correlated with some existing RAM, so that it has little informative incremental value, and that CAI has additional informational value to that of article influence. Harmonic mean rankings of the 13 RAM criteria for the 26 highly cited journals are also presented. Emphasizing the 2YIF of a journal to the exclusion of other informative RAM criteria is shown to lead to a distorted evaluation of journal performance and influence, especially given the informative value of several other RAM.     

STAR模型中的递归退势单位根检验研究

在STAR模型框架下,考虑时间序列具有线性确定性趋势成分,本文建立了一个递归退势单位根检验统计量,推导了其渐近分布;并在考虑初始条件情形下,对递归退势、OLS和GLS退势单位根检验统计量的有限样本性质进行了细致的比较研究。若忽略初始条件的影响,GLS退势和递归退势单位根检验统计量的检验势都显著高于OLS退势。随着初始条件的增大,GLS退势单位根检验统计量的检验势下降得比较厉害,递归退势单位根检验统计量的检验势较为稳定,且在样本量较大情形下更具优势。     

基于STAR模型的中国货币政策对产出影响的非对称性研究

对中国GDP增长率建立以可预期到的货币冲击、未预期到的正向货币冲击和未预期到的负向货币冲击滞后三期为转移变量的LSTAR模型,拟合效果良好,分析不同类型的货币冲击对产出的非线性和非对称性影响,给出可预期到的货币冲击、未预期到的正向货币冲击和未预期到的负向货币冲击的阀值,分别为20.03%、2%和1.58%,说明不同类型的货币冲击对产出呈现不同的非对称性影响,强弱机制的转换区间存在差异,且负向货币冲击的阀值小于正向货币冲击的阀值。研究结果表明中国的货币政策存在显著的非线性和非对称性特征,且紧缩性货币政策比扩张性货币政策更有效。