改进DTW下界约束的Granger多元时序LSTM预测模型

多元时序的因果预测研究是探讨复杂网络响应关系的热点问题。提出一种通过DTW的下界约束组合并改进的层级过滤器,与格兰杰因果验证法相结合验证其因果统计量,挖掘出有效信息实现有效降维,进一步输入LSTM预测模型进行因果预测。仿真实验利用开源的空气质量数据集进行定量和定性对比验证,该方法的损失函数训练曲线和测试曲线有较好的拟合度,表明该因果预测法是可行且有效的。

Granger Causality Analyses for Climatic Attribution

This review paper focuses on the application of the Granger causality technique to the study of the causes of recent global warming (a case of climatic attribution). A concise but comprehensive review is performed and particular attention is paid to the direct role of anthropogenic and natural forcings, and to the influence of patterns of natural variability. By analyzing both in-sample and out-of-sample results, clear evidences are obtained (e.g., the major role of greenhousegases radiative forcing in driving temperature, a recent causal decoupling between solar irradiance and temperature itself) together with interesting prospects of further research.

Granger Causality Test of Urban-rural Income Gap and Employment of Rural Labor Forces——A Case Study of Shouguang City

Taking Shouguang City in Shandong Province as an example, this article researches the mutual relationship between urban-rural income and employment of rural labor forces, and conducting cointegration test and Granger causality test on the variable sequences using statistical data. The results show that the average annual income of rural labor forces influences the income per capita of rural residents, and there is a Granger causality relationship between the income per capita of rural residents and urban employees' average wage. Engaging in production concerning agriculture, forestry, animal husbandry and fishery makes the total income per capita in rural areas of Shouguang City higher than the average wage of urban residents in Shouguang City, even in Weifang City. The comparative advantage in terms of income causes the city to loose attraction to rural residents in Shouguang City. The comparative advantage drives more rural labor forces in Shouguang City to engage in primary industry, thereby greatly reducing the pressure of employment and transfer of rural labor forces. Finally important following measures are put forward to promote employment and on-the-spot transfer of rural labor forces: vigorously propel agricultural industrialization; increase rural residents' income; improve the living conditions for rural residents.

Using granger-geweke causality model to evaluate the effective connectivity of primary motor cortex, supplementary motor area and cerebellum

Currently, Granger-Geweke causality models have been widely applied to investigate the dynamic direction relationships among brain regions. In a previous study, we have found that the right hand finger-tapping task can produce relatively reliable brain response. As an extension of our previous study, we developed an algorithm based on the classical Granger- Geweke causality model to further investigate the effective connectivity of three brain regions (left primary motor cortex (M1), supplementary motor area (SMA) and right cerebellum) that showed the most robust brain activations. Our computational results not only confirm the strong linear feedback among SMA, M1 and right cerebellum, but also demonstrate that M1 is the hub of these three regions indicated by the anatomy research. Moreover, the model predicts the high intermediate node density existing in the area between SMA and M1, which will stimulate the imaging experimentalists to carry out new experiments to validate this postulation.

Rural Financial Development and Rural Economic Efficiency Improvement Based on Granger Causality Test

Based on the co-integration test theory,Financial Interrelation Ratio(FIR),level of financial efficiency(LFE),level of financial development(LFD) and other indices evaluating the rural financial development are selected by Granger Causality Test.The rural loan balance(RLB),rural deposit balance(RDB),total rural output(TRO),fixed assets investment(FAI),Financial Interrelation Ratio(FIR),economic efficiency(EE),level of financial efficiency(LFE),and level of financial development(LFD) in the years 1979-2007 are collected.Graphical method intuitively reflects the development trend and historical track of relevant indices;and Granger Causality Test verifies the relationship between rural financial development level and rural economic efficiency in the years 1979-2007.Result shows that rural financial development level has significant impact on rural economic growth,but rural economic growth has no significant impact on rural financial development;and rural financial development also has insignificant promotion impact on rural economic efficiency.Thus,conclusions are obtained.Although rural financial development has made certain contribution to the development of rural economy,this kind of contribution is only reflected in total quantity,but not efficiency.Therefore,government should further strengthen the promotion function of financial development for economic efficiency,and gradually establish a virtuous circle system for rural finance and economic development.

The Impact of US Stock Market on the Co-Movements of BRIC Stock Markets—Evidence from Linear Conditional Granger Causality

This paper investigates the impact of the US stock market on the co-movements among the BRIC stock markets using conditional Granger causality which allows a comprehensive exploration on direct and indirect causality. The results from linear conditional causality test show a strong influence of the US stock market on the co-movements of BRIC. Our findings identify the US stock market which is the main inner factor making major contributions to the co-movements among the BRIC stock markets. Further, this study provides robust evidence that the co-movements cannot be significantly influenced by the common information factor. These findings show a more complete picture of the relationships between the US and the BRIC stock markets, offering important implications for policymakers and investors.

Insurance market density and economic growth in Eurozone countries:the granger causality approach

Background:This study examines the relationship between insurance market density(IMD)and economic growth.Methods:We employed Granger causality technique in 19 Eurozone countries for the period 1980-2014.We use three different indicators of IMD,namely life insurance density,non-life insurance density,and total insurance density.We particularly emphasize on whether Granger causality runs between IMD and economic growth both ways,one way,or not at all.Results:Our empirical result recognizes the presence of both unidirectional and bidirectional causality between insurance market density and economic growth.However,these results are mostly non-uniform across Eurozone countries.Conclusions:This study holds important policy implications-economic policies should recognize the differences in the insurance market density and economic growth in order to maintain sustainable economic growth in the Eurozone.

基于Time-Causality模型的供热用气量预测分析

目前关于时间序列预测的特征选择一直是研究的热点,但很少有学者分析多时间尺度下不同特征对预测的差异。提出基于Granger关系的Time-Causality预测模型,利用Granger关系进行特征选择,引入时间维度作为输入维度,并利用LSTM模型进行实验,在多时间尺度下分析预测供热用气量的特征。实验结果表明:Time-Causality模型能筛选到更有助于用气量预测的特征;从不同的时间尺度预测,所选取的特征不同;每个特征的预测作用也可能会随时间尺度的变化而变化。这为长期和短期预测提供理论和实践支持。

基于时变传染网络和分位数Granger因果检验的系统性风险传染研究

基于18个经济体760家金融机构SRISK系统性风险数据,采用时变参数向量自回归模型和广义方差分解法测度全球系统性风险的时变传染网络,进而采用分位数Granger因果检验考察各经济体对中国高分位段系统性风险的影响。研究结果表明,结合SRISK数据和时变传染网络能有效识别重大风险事件的发生;发达和新兴经济体均会产生风险净输出效应,且会通过直接输出或香港地区间接输出风险至中国内地;在全样本与2008年金融危机、欧债危机、中美贸易战和新冠疫情重大风险事件期间,中国皆为风险净溢入国且新冠疫情期间溢入效应达历史最高;美英两国在重大风险事件期间均对中国高分位段系统性风险产生显著影响,新冠疫情期间中国高分位段系统性风险遭受外部冲击的形势最为严峻。

Abnormal behavior detection by causality analysis and sparse reconstruction

A new approach for abnormal behavior detection was proposed using causality analysis and sparse reconstruction. To effectively represent multiple-object behavior, low level visual features and causality features were adopted. The low level visual features, which included trajectory shape descriptor, speeded up robust features and histograms of optical flow, were used to describe properties of individual behavior, and causality features obtained by causality analysis were introduced to depict the interaction information among a set of objects. In order to cope with feature noisy and uncertainty, a method for multiple-object anomaly detection was presented via a sparse reconstruction. The abnormality of the testing sample was decided by the sparse reconstruction cost from an atomically learned dictionary. Experiment results show the effectiveness of the proposed method in comparison with other state-of-the-art methods on the public databases for abnormal behavior detection.

Analysis of services trade and employment in China by co-integration and causality

This article describes a study by co-integration test and Granger causality test on the relationships between China's services trades and employment using the data of services trade from the WTO website and the employment data from China Statistic Yearbook for the years from 1982 to 2003. Co-integration test showed that 1% increase in export value and import value of services created respectively 0.205% and 0.068 7% more job opportunities in the service sector. Both export and import of services impacted positively on employment in service industry, and export did more than import. However, in the short run, the impacts of services export and import on employment in service industry were both very small, though positive; and the impacts of employment in service industry on both export and import of services were very big, but not stable. Granger causality test indicated that employment in service industry was a Granger cause of services export. The findings highlight the importance of facilitating services import and reducing import barriers, and suggest that the competitiveness of China's labor- intensive services trade can be exploited to boost services export and help employment in service sector, and that the structure of services trade should be optimized by shifting from labor-intensive to knowledge-and technology-intensive services thus to enhance China's competitiveness of services export.

Correlation analysis and causality test between Ludong-Huanghai block and South Japan

In this paper, we make a comparative analysis and correlation test for the seismic activities in the South Japan and the Ludong-Huanghai block （a secondary tectonic unit in the North China） and approach the relationship between the energy release processes of these two areas by using co-integration analysis and Granger causality test for the time series of random variables. The results show that the seismic activities in these two areas are correlative and synchronous to a certain extent, and their release series of cumulative strain energy are contemporaneously correlative. Both energy series are first-order difference stationary processes and there is secular and steady co-integration between them. We make a positive analysis on the first-order difference energy series through Granger causality test based on vector error correction （VEC） model and find there is unilateral Granger causality and prominent co-integration between the two energy release processes.

Robust Parameter Identification Method of Adhesion Model for Heavy Haul Trains

A robust parameter identification method based on Kiencke model was proposed to solve the problem of the parameter identification accuracy being affected by the rail environment change and noise interference for heavy-duty trains. Firstly, a Kiencke stick-creep identification model was constructed, and the parameter identification task was transformed into a quadratic programming problem. Secondly, an iterative algorithm was constructed to solve the problem, into which a time-varying forgetting factor was added to track the change of the rail environment, and to solve the uncertainty problem of the wheel-rail environment. The Granger causality test was adopted to detect the interference, and then the weights of the current data were redistributed to solve the problem of noise interference in parameter identification. Finally, simulations were carried out and the results showed that the proposed method could track the change of the track environment in time, reduce the noise interference in the identification process, and effectively identify the adhesion performance parameters.

Causality between bank’s major activities and economic growth:evidences from Pakistan

Background:Banking is an important sector of Pakistan’s economy.It is general consideration that bank’s major activities saving and lending have positive impact on economic growth.So the aim of this study is to investigate this consideration and also investigate that either growth led deposits and credits,or deposit and credits led growth means the purpose of this study is to investigate the direction of this relationship.Methods:Johansen test of Co-integration and Granger Causality is employed by using time series data of Pakistan from 1961 to 2013.Results:The results show that two major activities of banking sector that are saving and lending don’t have any long run or short run causality towards economic growth so the general consideration of positive impact of these activities proved wrong in case of Pakistan.However there is unidirectional causality running from GDP growth to credit provided by banking sector which shows that economic prosperity or economic growth will have a major impact on lending activities of banks meaning that demand following hypothesis is true for Pakistan in case of GDP and Bank’s credit or we can say that growth led Bank’s credit in Pakistan.Conclusions:Hence Government and central bank should make policies by keeping this fact in consideration that bank’s two major activities that are saving and lending does not have impact on GDP growth.There might be other factors which influence economic growth of Pakistan more than banking sector these activities,which can be bank’s profitability,human resource,technology,infrastructure and other sectors of the economy.However GDP growth affects bank’s lending activities so during high economic growth year central bank and private bank’s management should introduce easy loans for businesses and industries and during poor economic growth years personal loan’s new schemes should be introduce by banks.

Causality Relationship between Energy Consumption and Economic Growth in Brazil

This study has investigated the relationship between energy consumption and economic growth in Brazil during the period of 1980-2008. The co-integration test indicates a long-run equilibrium relationship between variables, andenergy consumption appears to be real GDP elastic. This elasticity suggests that energy consumption has a great positive influence on changes in income. The causality results from the error correction model reveal a unidirectional short-run causality from energy consumption to economic growth and a bidirectional strong causality between them. These findings suggest that Brazil should adopt a dual strategy of increasing investment in energy infrastructure, and stepping up energy conservation policies to reduce any unnecessary waste of energy, in order to avoid having a negative effect on economic growth by reducing energy consumption. In contrast, energy conservation is expected to increase the efficient use of energy and, therefore, enhance economic growth.

山西省能源消费和经济增长关系研究:基于Johansen协整检验和Granger因果关系检验

山西省是能源消费大省,认识经济增长与能源消费的内在关系,对于促进山西省经济社会可持续发展有重大意义。本文利用山西省1980～2010年能源消费总量和经济增长数据,通过Johansen检验发现两者为协整变量,且两者之间的长期均衡关系表明第t年的GDP和第t-1年的能源消费总量对第t年的能源消费有明显的影响。通过Granger因果关系检验发现GDP是能源消费总量的Granger原因,反之则不成立。提出转变经济增长方式、实施节能技术改造、完善能源法律与政策的建议。

CEEMD双层分解和Granger因果变量选择风电功率预测

针对风电功率时间序列具有高度随机波动性而无法精准预测的问题,提出一种基于完备集成经验模态分解(CEEMD)、Granger因果关系检验和长短时记忆网络的新型混合预测方法用于预测风电功率。首先,为研究风电功率和风速的隐性相关性,通过CEEMD算法对风电功率和风速时间序列分别进行序列分解,实现双层分解。其次,通过Granger因果关系方法对各风速分量与各风电功率分量进行因果关系检验,分析风电功率分量与各风速分量间的相关性,以此实现各风电功率分量的输入变量选择。最后,采用长短时记忆网络对各风电功率分量进行预测,并集成得到最终的风电功率预测结果。通过风电厂的实际数据进行了试验,并与多个应用广泛的经典模型进行对比,结果表明该方法的预测精度取得了大幅度提高,能够对风电功率实现精准预测。

Granger因果关系时空图推理的群体行为分析

因果关系普遍存在于群体交互行为中,体现出主动体行为对被动体行为的有向影响.因果关系检测的难点在于交互双方的行为具有复杂的时间动态性.现有方法使用循环神经网络,来描述交互关系的时间变化特性,并使用时间注意力机制,来描述时间依赖关系.上述方法忽视了对多人依赖关系的分析,难以区分交互双方中的主动行为者和被动行为者.本文设计了一种基于Granger因果关系的时空图推理模型,来学习交互双方的主动和被动关系.为了实现Granger因果关系检测,该模型对单个个体时序特征进行自回归建模,来描述行为对个体自己的依赖.该模型对两个个体时序特征进行相关回归建模,来描述行为对两个个体的依赖.该模型通过比较自回归误差和相关回归误差,当自回归误差明显大于相关回归误差,则说明相关个体改变了另一方个体的行为特征,从而检测出相关个体为主动个体,另一方为被动个体.相关回归模型考虑了多种时间延迟量的两个个体的时序特征序列,用于学习两个个体之间行为的时间延迟量.该时间延迟量用于将主动个体时间特征与被动个体时间特征进行对齐.时间对齐后的主动个体特征提供了被动个体的时间和空间上下文特征,并与被动个体特征进行通道级的融合.为了充分描述个体之间的外观模式,位置约束,因果关系的交互关系,该模型构建多尺度外观的因果图,并使用图推理学习融合上下文的个体特征和群体特征.本文对Granger因果关系检测进行消融分析,并说明时间延迟量,交互融合通道比例,多尺度图推理,能够有效改善个体特征、群体特征的描述能力.本文方法在Volleyball和Collective Activity数据集上优于现有群体行为识别方法.本文的可视化结果说明Granger因果关系可以捕获群体中关键的交互关系.

The time‑varying causal relationship between the Bitcoin market and internet attention

The increasing attention on Bitcoin since 2013 prompts the issue of possible evidence for a causal relationship between the Bitcoin market and internet attention.Taking the Google search volume index as the measure of internet attention,time-varying Granger causality between the global Bitcoin market and internet attention is examined.Empirical results show a strong Granger causal relationship between internet attention and trading volume.Moreover,they indicate,beginning in early 2018,an even stronger impact of trading volume on internet attention,which is consistent with the rapid increase in Bitcoin users following the 2017 Bitcoin bubble.Although Bitcoin returns are found to strongly affect internet attention,internet attention only occasionally affects Bitcoin returns.Further investigation reveals that interactions between internet attention and returns can be amplified by extreme changes in prices,and internet attention is more likely to lead to returns during Bitcoin bubbles.These empirical findings shed light on cryptocurrency investor attention theory and imply trading strategy in Bitcoin markets.