Granger Causality Method Research Articles

The relationship between woody biomass consumption and economic growth: Nonlinear ARDL and causality

In this paper, the structure of the relationship between woody biomass energy consumption and real per Capita GDP was analyzed in the period of 1980–2012 for the selected African countries by ARDL (Autoregressive Distributed Lag), nonlinear ARDL, Granger causality and forecast error variance decomposition methods. After a symmetric relationship between woody biomass energy consumption and economic growth was determined by the nonlinear ARDL (NARDL) model, ARDL and Granger Causality methods were applied. According to results of the Granger Causality method, there is a unidirectional causality running from economic growth to woody biomass energy consumption for Botswana, Cameroon, Uganda, and Zambia and from woody biomass energy consumption to economic growth for Burkina Faso, Malawi, Central African Republic, Namibia, Côte d’Ivoire, Djibouti, Gabon and Zimbabwe. The bidirectional causality was supported for Kenya, Lesotho, Madagascar and Togo. Lastly, forecast error variance decomposition method was applied to support the results obtained from Granger Causality method. The forecast error variance decomposition results of real per Capita GDP and woody biomass energy consumption showed that woody biomass energy and real per Capita GDP made the important contribution to the forecast error variance of itself and each other.

Bi-Directional Causality between Working Capital Management and Profitability: Empirical Study of Indian Listed Firms

Management of short term funds and their disbursement plays a vital role in deciding fate of entity’s financial soundness and future prospect. Thus efficient working capital management is prerequisite for business success so has not only remained orbit of many theoretical and empirical studies but also great concern for management and academic experts. Empirical literature in Indian context on this topic not only presents ambiguous results, but is centered mainly on the possible impact efficient working capital management levels on profitability of the companies, disregarding the possibility of reverse causality running from profitability to effective liquidity and working capital management efficiency, except few recent studies from developed nations. Olarewaju M.O & Adeyemi K.O (2013); Awad, I & Jayyar F (2013). Current study is an attempt to shed light on bidirectional causal relationship between working capital management components like liquidity and cash conversion cycle proxies efficiency of the management in formulating and executing growth and sustainability oriented policies and profitability in the Indian listed firms for the period last one decade through use of econometric model of granger causality and other related methods according to need of study. The results failed to support theoretical assumption and strengthened the prior works and revealed that there is no causal relationship but while taking lag of one year results favored the casual relationship between efficiency liquidity and profitability. The study addressing the current issues may frame consciousness among managers and academicians and help to rule out myths and touch the modern horizons of managing daily financial requirements.

ISLAMIC FINANCE DEVELOPMENT AND ECONOMIC GROWTH: EMPIRICAL EVIDENCE FROM TURKEY

This work is a study on Islamic finance development and economic growth nexus for Turkey. It employs the econometric methods of unit root, co-integration, and Granger causality in a VECM framework; and the results, which are robust to all measures of Islamic finance development, show a unidirectional short and long run causality from Islamic finance development to economic growth. Hence, it is recommended that policy makers increase their efforts in promoting Islamic finance in Turkey. Keywords: Islamic finance development, Granger causality, Turkey

Learning effective connectivity from fMRI using autoregressive hidden Markov model with missing data

BackgroundEffective connectivity (EC) analysis of neuronal groups using fMRI delivers insights about functional-integration. However, fMRI signal has low-temporal resolution due to down-sampling and indirectly measures underlying neuronal activity. New methodThe aim is to address above issues for more reliable EC estimates. This paper proposes use of autoregressive hidden Markov model with missing data (AR-HMM-md) in dynamically multi-linked (DML) framework for learning EC using multiple fMRI time series. In our recent work (Dang et al., 2016), we have shown how AR-HMM-md for modelling single fMRI time series outperforms the existing methods. AR-HMM-md models unobserved neuronal activity and lost data over time as variables and estimates their values by joint optimization given fMRI observation sequence. ResultsThe effectiveness in learning EC is shown using simulated experiments. Also the effects of sampling and noise are studied on EC. Moreover, classification-experiments are performed for Attention-Deficit/Hyperactivity Disorder subjects and age-matched controls for performance evaluation of real data. Using Bayesian model selection, we see that the proposed model converged to higher log-likelihood and demonstrated that group-classification can be performed with higher cross-validation accuracy of above 94% using distinctive network EC which characterizes patients vs. controls. The full data EC obtained from DML-AR-HMM-md is more consistent with previous literature than the classical multivariate Granger causality method. ComparisonThe proposed architecture leads to reliable estimates of EC than the existing latent models. ConclusionsThis framework overcomes the disadvantage of low-temporal resolution and improves cross-validation accuracy significantly due to presence of missing data variables and autoregressive process.

Do High Speed Railways Lead to Urban Economic Growth in China?: A Panel Data Study of China's Cities

This paper investigates the impact of high-speed railroads (HSR) on city-level economic activity using a new dataset for approximately 200 cities in China from 2007-2014. We apply panel Granger causality methods to assess whether increases in a city’s accessibility increases GDP growth, GDP per capita growth and wage growth. Or does causality run the opposite way – does rising economic growth boost accessibility? Results document that increases in accessibility lead to significant and relatively large increases in GDP growth on the city-level; further, the benefits substantially out-weigh HSR’s fixed costs, depreciation and subsidies. Out-of-sample methods document the importance of increases in HSR in forecasting GDP growth. Monte Carlo simulations document the usefulness of OLS and out-of-sample tests in assessing panel Granger Causality tests.

Оценка работоспособности метода причинности по Грейнджерудля выявления однонаправленной связи при наличии общей внешней низкочастотной помехи

Оценка работоспособности метода причинности по Грейнджерудля выявления однонаправленной связи при наличии общей внешней низкочастотной помехи

Stock Market and Economic Growth in Nigeria

This study investigates the short run effect, long run effect and causal relationship between stock market and economic growth in Nigeria. The Augmented Dickey Fuller unit root test, Ordinary Least Squares, Johansen Co-integration test and Pairwise granger causality methods were applied to the variables. The OLS result showed that the all share index had a significant but negative relationship with economic growth; The Johansen co-integration test showed that a long run relationship exists between the stock market performance and economic growth in Nigeria in the long run while the Granger causality test results showed that stock market performance does not granger cause economic growth but economic growth granger causes stock market performance at 5 percent significance level. The study suggested some of the possible reasons for the negative impact of stock market on the Nigerian economic growth and recommended that efforts should be made to improve the stock market performance to have a positive effect on the real gross domestic product of Nigeria overtime.

Synchrony dynamics underlying effective connectivity reconstruction of neuronal circuits

Reconstruction of effective connectivity between neurons is essential for neural systems with function-related significance, characterizing directionally causal influences among neurons. In this work, causal interactions between neurons in spinal dorsal root ganglion, activated by manual acupuncture at Zusanli acupoint of experimental rats, are estimated using Granger causality (GC) method. Different patterns of effective connectivity are obtained for different frequencies and types of acupuncture. Combined with synchrony analysis between neurons, we show a dependence of effective connection on the synchronization dynamics. Based on the experimental findings, a neuronal circuit model with synaptic connections is constructed. The variation of neuronal effective connectivity with respect to its structural connectivity and synchronization dynamics is further explored. Simulation results show that reciprocally causal interactions with statistically significant are formed between well-synchronized neurons. The effective connectivity may be not necessarily equivalent to synaptic connections, but rather depend on the synchrony relationship. Furthermore, transitions of effective interaction between neurons are observed following the synchronization transitions induced by conduction delay and synaptic conductance. These findings are helpful to further investigate the dynamical mechanisms underlying the reconstruction of effective connectivity of neuronal population.

An Evaluation of the Nexus Between Banking Competition and Efficiency in Zimbabwe

This study investigates the relationship between cost and revenue efficiency, and competition in the banking system in Zimbabwe. Competition was approximated using the Lerner Index, and efficiency, using the data envelopment analysis. The Granger causality method was applied to determine the causal relationship between efficiency and competition. The study established that the banks operated under monopolistic competition during the period 2009-2014. The data envelopment analysis found that banks in Zimbabwe operate outside their revenue and cost efficiency potential, experiencing inefficiency levels of around 30 per cent. The Granger causality test suggests that revenue and cost efficiency positively Granger causes market power. This means that an increase in cost and revenue efficiency leads to a decline in competition, which implies that bank regulators face a tradeoff and should moderate their application of procompetitive policies. The results further suggest that competition positively impacts cost efficiency supporting the institution of procompetitive policies so as to stimulate cost efficiency.

Altered effective connectivity network of the thalamus in post-traumatic stress disorder: a resting-state FMRI study with granger causality method

Post-traumatic stress disorder (PTSD) is an anxiety disorder that can develop following a traumatic event. Previous studies have found abnormal functional connectivity between the thalamus and other brain regions. However, the traditional functional connectivity method cannot investigate the directional flow of the influence in PTSD. In the present study, we used an effective connectivity method based on Granger causality to explore altered direction of causal information flow within a network associated with the thalamus in PTSD. Employing this method, we found that PTSD patients exhibited increased influence from thalamus to middle/inferior frontal gyrus and insula, and increased bidirectional influences between thalamus and medial prefrontal cortex compared to healthy controls. This is the first study to reveal a network of abnormal effective connectivity in PTSD. In addition, using the machine learning approach, we found that the altered functional measurements could differentiate patients from healthy controls. Our findings may have important implications for the pathophysiological basis underlying PTSD.

Investor Reaction to Consumer Sentiment: The Case of Manufacturing Firms in Indonesia

This study aims to determine the influence of industrial workers concentration on the consumer confidence index and the influence of consumer confidence index on the capital market, especially stock issuers from manufacturing industry sector. The data used in this research is secondary data with the sample of consumer confidence index taken from Jakarta and Surabaya as well as 47 manufacturing industry stock issuers listed in Indonesia Stock Exchange. This research isconducted by using Granger Causality method. The results generally show that there is no influence found for regional consumer confidence index with large manufacturing industry and regional consumer confidence index with relatively small manufacturing industry towards the national consumer confidence index. Research has also managed to find a significant influence of consumer confidence index on the price of stocks issued by several manufacturing companies.

Inferring Weighted Directed Association Network from Multivariate Time Series with a Synthetic Method of Partial Symbolic Transfer Entropy Spectrum and Granger Causality.

Complex network methodology is very useful for complex system explorer. However, the relationships among variables in complex system are usually not clear. Therefore, inferring association networks among variables from their observed data has been a popular research topic. We propose a synthetic method, named small-shuffle partial symbolic transfer entropy spectrum (SSPSTES), for inferring association network from multivariate time series. The method synthesizes surrogate data, partial symbolic transfer entropy (PSTE) and Granger causality. A proper threshold selection is crucial for common correlation identification methods and it is not easy for users. The proposed method can not only identify the strong correlation without selecting a threshold but also has the ability of correlation quantification, direction identification and temporal relation identification. The method can be divided into three layers, i.e. data layer, model layer and network layer. In the model layer, the method identifies all the possible pair-wise correlation. In the network layer, we introduce a filter algorithm to remove the indirect weak correlation and retain strong correlation. Finally, we build a weighted adjacency matrix, the value of each entry representing the correlation level between pair-wise variables, and then get the weighted directed association network. Two numerical simulated data from linear system and nonlinear system are illustrated to show the steps and performance of the proposed approach. The ability of the proposed method is approved by an application finally.

Changes in corticocortical and corticohippocampal network during absence seizures in WAG/Rij rats revealed with time varying Granger causality.

Spike-and-wave discharges (SWDs) recorded in the cortical EEGs of WAG/Rij rats are the hallmark for absence epilepsy in this model. Although this type of epilepsy was long regarded as a form of primary generalized epilepsy, it is now recognized that there is an initiation zone - the perioral region of the somatosensory cortex. However, networks involved in spreading the seizure are not yet fully known. Previously, the dynamics of coupling between different layers of the perioral cortical region and between these zones and different thalamic nuclei was studied in time windows around the SWDs, using nonlinear Granger causality. The aim of the present study was to investigate, using the same method, the coupling dynamics between different regions of the cortex and between these regions and the hippocampus. Local field potentials were recorded in the frontal, parietal, and occipital cortices and in the hippocampus of 19 WAG/Rij rats. To detect changes in coupling reliably in a short time window, in order to provide a good temporal resolution, the innovative adapted time varying nonlinear Granger causality method was used. Mutual information function was calculated in addition to validate outcomes. Results of both approaches were tested for significance. The SWD initiation process was revealed as an increase in intracortical interactions starting from 3.5s before the onset of electrographic seizure. The earliest preictal increase in coupling was directed from the frontal cortex to the parietal cortex. Then, the coupling became bidirectional, followed by the involvement of the occipital cortex (1.5s before SWD onset). There was no driving from any cortical region to hippocampus, but a slight increase in coupling from hippocampus to the frontoparietal cortex was observed just before SWD onset. After SWD onset, an abrupt drop in coupling in all studied pairs was observed. In most of the pairs, the decoupling rapidly disappeared, but driving force from hippocampus and occipital cortex to the frontoparietal cortex was reduced until the SWD termination. Involvement of multiple cortical regions in SWD initiation shows the fundamental role of corticocortical feedback loops, forming coupling architecture and triggering the generalized seizure. The results add to the ultimate aim to construct a complete picture of brain interactions preceding and accompanying absence seizures in rats.

Empirical analysis of interaction between promotion expenditures and tourism the case of Turkey

The Turkish tourism sector is among the first places in international markets in terms of number of visiting tourists. But the same situation is not valid in terms of tourism revenue. At this point, tourism promotion becomes important for the Turkish economy. The Ministry of Culture and Tourism arranges promotional activities in different regions of the world to increase the number of tourists and revenue of tourism sector. But it is possible to interpret that tourism demand is not sufficient compare to potential of the country because of absence of effective and planned promotion policy. The aim of this study is to test interaction between tourism promotion expenditures, tourism revenue and number of tourists by employing recently developed Vector Autoregressive based Toda–Yamamoto and conventional Granger causality methods. In the study, annual data belonging to period between years 1990 and 2012 is used. Results of the empirical analyses give evidences about the relation between tourism promotion expenditures, tourism revenue and number of tourists. Findings obtained from both conventional Granger and Toda – Yamamoto causality tests imply that there is a causation linkage running from tourism promotion expenditures to number of tourists visiting Turkey. Results also indicate that there is no causal relationship between tourism promotion expenditures and tourism revenue. Keywords: Tourism, tourism demand, promotion expenditure, tourism income JEL Classification: C22,L83,Z33

Gamma band directional interactions between basal forebrain and visual cortex during wake and sleep states

The basal forebrain (BF) is an important regulator of cortical excitability and responsivity to sensory stimuli, and plays a major role in wake-sleep regulation. While the impact of BF on cortical EEG or LFP signals has been extensively documented, surprisingly little is known about LFP activity within BF. Based on bilateral recordings from rats in their home cage, we describe endogenous LFP oscillations in the BF during quiet wakefulness, rapid eye movement (REM) and slow wave sleep (SWS) states. Using coherence and Granger causality methods, we characterize directional influences between BF and visual cortex (VC) during each of these states. We observed pronounced BF gamma activity particularly during wakefulness, as well as to a lesser extent during SWS and REM. During wakefulness, this BF gamma activity exerted a directional influence on VC that was associated with cortical excitation. During SWS but not REM, there was also a robust directional gamma band influence of BF on VC. In all three states, directional influence in the gamma band was only present in BF to VC direction and tended to be regulated specifically within each brain hemisphere. Locality of gamma band LFPs to the BF was confirmed by demonstration of phase locking of local spiking activity to the gamma cycle. We report novel aspects of endogenous BF LFP oscillations and their relationship to cortical LFP signals during sleep and wakefulness. We link our findings to known aspects of GABAergic BF networks that likely underlie gamma band LFP activations, and show that the Granger causality analyses can faithfully recapitulate many known attributes of these networks.

Investigating causality in international air freight and business travel: The case of Australia

Few studies have examined the link between air cargo and business travel, despite there being a generally accepted understanding that these two variables are inextricably related to each other. This paper examines the relationship between air cargo and business travel at the international level and analyses how these two variables are causally related. Moreover, we break down the sample into three major Australian states (New South Wales, Queensland, and Victoria), as each possesses a distinct flavour in trade and commerce. Utilising Granger causality methods, we have found evidence that there is a direct causal relationship between business travel and air cargo in the short run, and a bi-directional relationship in periods of 12 months and longer. The nature of the Granger causality at the state-level substantially differs from state to state, suggesting that the economic landscape of Australia’s local economy has a significant impact on the air cargo and business travel relationship.

A study of causality structure and dynamics in industrial electricity consumption based on Granger network

Abstract Based on industrial electricity consumption, we model industrial networks by Granger causality method and MST (minimum spanning tree), and then further stick onto an industrial coupling mechanism from energy-consumption perspective. First, we construct Granger causality networks of five provinces in South China of GD, GX, GZ, HN and YN based on their industrial electricity consumption data, and we demonstrate from a network-topology perspective: the distribution of weight of links of all industrial electricity-consumption Granger causality networks approximately follows power-law distribution, revealing a phenomenon that few industries may bring a tremendous influence on the rest. Moreover, correlation analysis between weight and degree of a node shows that in most Granger causality networks, both span and strength of influence of a given industry will significantly increase. Further, we analyze the relationship between the thresholds of Granger causality significance and density of corresponding networks. Results show GD and HN could be classified into a group with relatively greater global differentiation in industries and unbalanced industrial development, however, GX, GZ and YN are grouped as second cluster with relatively balanced industrial development. Furthermore, using Chu–Liu–Edmonds MST algorithm, we extract graphs of MSTs or maximal cliques from industrial electricity-consumption Granger causality networks, and research on energy transmission structure, feedback loop, and bootstrap reliability. By analyzing MSTs, we find that only GD, GX and YN can be extracted with MST graphs, and capture the probable transmission routes of key nodes. Besides we illustrate all three MST graphs are involved with feedback loops structures with various characteristics: GX has complete feed-forward section, feed-back section and feedback loop section; YN has only feed-forward section and feedback loop section; GD has multiple feedback loops section. Finally, we conduct bootstrap reliability tests on MSTs. Results show branches of reliability of GD, GX and YN are decentralized while those feedback loops sections are only concentrated on highly-reliable branches. As neither HN nor GZ can be extracted with MST graphs, we characterize them by maximal cliques. It is demonstrated that both industrial systems of HN and GZ are significantly grouped into two independent branches and those internal industries inside independent branches are highly correlated. However from perspectives of whole South China, the causal relationship is only converged on a few of industries. For regions without MST graphs like HN and GZ, the reliability of links is also greater than that of GD, GX and YN.

The impact of trade openness on global carbon dioxide emissions: Evidence from the top ten emitters among developing countries

This study aims to analyze the relationship between carbon dioxide (CO2) emissions, trade openness, real income and energy consumption in the top ten CO2 emitters among the developing countries; namely China, India, South Korea, Brazil, Mexico, Indonesia, South Africa, Turkey, Thailand and Malaysia over the period of 1971–2011. In addition, the possible presence of the EKC hypothesis is investigated for the analyzed countries. The Zivot–Andrews unit root test with structural break, the bounds testing for cointegration in the presence of structural break and the VECM Granger causality method are employed. The empirical results indicate that (i) the analyzed variables are co-integrated for Thailand, Turkey, India, Brazil, China, Indonesia and Korea, (ii) real income, energy consumption and trade openness are the main determinants of carbon emissions in the long run, (iii) there exists a number of causal relations between the analyzed variables, (iv) the EKC hypothesis is validated for Turkey, India, China and Korea. Robust policy implications can be derived from this study since the estimated models pass several diagnostic and stability tests.

The Causality between Healthcare Resources and Health Expenditures in Turkey. A Granger Causality Method

The aim of this study was to evaluate the causality between healthcare resources and health expenditure in Turkey over the period from 1975 to 2013. The empirical modeling was based on how GDP per capita, the number of doctor and number of hospital beds had an impact on the growth of health spending per capita. Data were gathered from the statistical databases of Turkstat, World Bank Indicators and OECD Health Data. Granger Var method was used to investigate causality between variables. Eviews 9 software was performed for the tests. At the end of the analysis, it was found out that, health expenditures per capita were affected by the number of physician per 1000 to population and it had an effect on GDP per capita. These results are expected to provide important information to health policymakers to understand which variables have an impact on dynamics of health expenditures in Turkey while they plan and control their limited resources.

The Relationship between CO2 Emission, Energy Consumption, Urbanization and Trade Openness for Selected CEECs

This paper investigates the relationship between CO2 emission, real GDP, energy consumption, urbanization and trade openness for 10 for selected Central and Eastern European Countries (CEECs), including, Albania, Bulgaria, Croatia, Czech Republic, Macedonia, Hungary, Poland, Romania, Slovak Republic and Slovenia for the period of 1991–2011. The results show that the environmental Kuznets curve (EKC) hypothesis holds for these countries. The fully modified ordinary least squares (FMOLS) results reveal that a 1% increase in energy consumption leads to a %1.0863 increase in CO2 emissions. Results for the existence and direction of panel Vector Error Correction Model (VECM) Granger causality method show that there is bidirectional causal relationship between CO2 emissions - real GDP and energy consumption-real GDP as well.