Short run and long run causality in time series: Inference

We propose methods for testing hypotheses of non-causality at various horizons, as defined in Dufour and Renault (1998, Econometrica). We study in detail the case of VAR models and we propose linear methods based on running vector autoregressions at different horizons. While the hypotheses considered are nonlinear, the proposed methods only require linear regression techniques as well as standard Gaussian asymptotic distributional theory. Bootstrap procedures are also considered. For the case of integrated processes, we propose extended regression methods that avoid nonstandard asymptotics. The methods are applied to a VAR model of the U.S. economy.

Finite-Sample Simulation-Based Inference in VAR Models with Applications to Order Selection and Causality Testing

Statistical tests in vector autoregressive (VAR) models are typically based on large-sample approximations, involving the use of asymptotic distributions or bootstrap techniques. After documenting that such methods can be very misleading even with fairly large samples, especially when the number of lags or the number of equations is not small, we propose a general simulation-based technique that allows one to control completely the level of tests in parametric VAR models. In particular, we show that maximized Monte Carlo tests [Dufour (2002)] can provide provably exact tests for such models, whether they are stationary or integrated. Applications to order selection and causality testing are considered as special cases. The technique developed is applied to quarterly and monthly VAR models of the U.S. economy, comprising income, money, interest rates and prices, over the period 1965-1996.

Temporal causality between the exchange rate and the trade balance : the case of Brazil

The paper assesses the impact of intemational relative prices and domestic expenditure variables on Brazil' s foreign trade performance in the first half of the 1990s. It has been argued that the appreciation of the Real since 1994 has had a detrimental impact of the country's trade balance. However, using temporal precedence analysis, our results do not indicate that the trade balance is strongly affected by intemational rei ative prices, such as the exchange rate. Instead, domestic expenditure variables appear to be more powerful determinant of the country' s trade performance in recent years. Granger and error correction causality techniques are used to determine temporal precedence between the trade balance and the exchange rate in the period under examination. Our findings shed light on the debate over the sustainability of recent exchange rate-anchored macroeconomic stabilisation programmes, which is a topic that has encouraged a lot of debate among academics and practitioners.

Causality Relationships between Total Exports with Agricultural and Manufacturing GDP in Tanzania

This paper, investigates causal relationships among agriculture, manufacturing and export in Tanzania by using time series data for the period between 1970 and 2005. The empirical results show in both sectors there is Granger causality where agriculture causes both exports and manufacturing. Exports also cause both agricultural GDP and manufacturing GDP and any two variables out of three jointly cause the third one. There is also some evidence that manufacturing does not cause export and agriculture. Regarding cointegration, pairwise agricultural GDP and export are cointegrated, export and manufacture are cointegrated. Agriculture and manufacture are cointegrated but they are lag sensitive. However, three variables, manufacturing, export and agriculture both together are cointegrated showing that they share long run relation and this has important economic implications.

Electroencephalogram based Causality Graph Analysis in Behavior Tasks of Parkinson’s Disease Patients

Electroencephalographic (EEG) signals of the human brains represent electrical activities for a number of channels recorded over a the scalp. The main purpose of this thesis is to investigate the interactions and causality of different parts of a brain using EEG signals recorded during a performance subjects of verbal fluency tasks. Subjects who have Parkinson's Disease (PD) have difficulties with mental tasks, such as switching between one behavior task and another. The behavior tasks include phonemic fluency, semantic fluency, category semantic fluency and reading fluency. This method uses verbal generation skills, activating different Broca's areas of the Brodmann's areas (BA44 and BA45). Advanced signal processing techniques are used in order to determine the activated frequency bands in the granger causality for verbal fluency tasks. The graph learning technique for channel strength is used to characterize the complex graph of Granger causality. Also, the support vector machine (SVM) method is used for training a classifier between two subjects with PD and two healthy controls. Neural data from the study was recorded at the Colorado Neurological Institute (CNI). The study reveals significant difference between PD subjects and healthy controls in terms of brain connectivities in the Broca's Area BA44 and BA45 corresponding to EEG electrodes. The results in this thesis also demonstrate the possibility to classify based on the flow of information and causality in the brain of verbal fluency tasks. These methods have the potential to be applied in the future to identify pathological information flow and causality of neurological diseases.

Causality and synchronisation in complex systems with applications to neuroscience

This thesis presents an investigation, of synchronisation and causality, motivated by problems in computational neuroscience. The thesis addresses both theoretical and practical signal processing issues regarding the estimation of interdependence from a set of multivariate data generated by a complex underlying dynamical system. This topic is driven by a series of problems in neuroscience, which represents the principal background motive behind the material in this work. The underlying system is the human brain and the generative process of the data is based on modern electromagnetic neuroimaging methods . In this thesis, the underlying functional of the brain mechanisms are derived from the recent mathematical formalism of dynamical systems in complex networks. This is justified principally on the grounds of the complex hierarchical and multiscale nature of the brain and it offers new methods of analysis to model its emergent phenomena. A fundamental approach to study the neural activity is to investigate the connectivity pattern developed by the brain’s complex network. Three types of connectivity are important to study: 1) anatomical connectivity refering to the physical links forming the topology of the brain network; 2) effective connectivity concerning with the way the neural elements communicate with each other using the brain’s anatomical structure, through phenomena of synchronisation and information transfer; 3) functional connectivity, presenting an epistemic concept which alludes to the interdependence between data measured from the brain network. The main contribution of this thesis is to present, apply and discuss novel algorithms of functional connectivities, which are designed to extract different specific aspects of interaction between the underlying generators of the data. Firstly, a univariate statistic is developed to allow for indirect assessment of synchronisation in the local network from a single time series. This approach is useful in inferring the coupling as in a local cortical area as observed by a single measurement electrode. Secondly, different existing methods of phase synchronisation are considered from the perspective of experimental data analysis and inference of coupling from observed data. These methods are designed to address the estimation of medium to long range connectivity and their differences are particularly relevant in the context of volume conduction, that is known to produce spurious detections of connectivity. Finally, an asymmetric temporal metric is introduced in order to detect the direction of the coupling between different regions of the brain. The method developed in this thesis is based on a machine learning extensions of the well known concept of Granger causality. The thesis discussion is developed alongside examples of synthetic and experimental real data. The synthetic data are simulations of complex dynamical systems with the intention to mimic the behaviour of simple cortical neural assemblies. They are helpful to test the techniques developed in this thesis. The real datasets are provided to illustrate the problem of brain connectivity in the case of important neurological disorders such as Epilepsy and Parkinson’s disease. The methods of functional connectivity in this thesis are applied to intracranial EEG recordings in order to extract features, which characterize underlying spatiotemporal dynamics before during and after an epileptic seizure and predict seizure location and onset prior to conventional electrographic signs. The methodology is also applied to a MEG dataset containing healthy, Parkinson’s and dementia subjects with the scope of distinguishing patterns of pathological from physiological connectivity.

Causality in crude oil prices

Economic media inform on prices of three well established crude oil benchmarks: Brent, WTI and Dubai Fateh. The relevance of these is however declining with their low output - motivating investigation of the pricing dynamics. We apply Granger causality tests to study the price dependencies of 32 crude oils. The aim is to establish what crudes are setting the prices and what crudes are just following the general market trends. The investigation is performed globally as well as for different quality, geographical and organisational segments. The results indicate that crude oil price analysts should follow at least four different crudes that are good price indicators. WTI and Brent still lead the market, but they are not the only crude prices worth paying attention to. In particular, Russian Urals drives global prices in a significant way, and Iran Seri Kerir is a significant price setter within OPEC. Dubai Fateh does not display any significant influence as a price setter, which confirms the lack of dominant benchmark within the segment of medium quality crudes.

Causality in crude oil prices

Crude oil markets witness growing disparity between the quality of crudes supplied and demanded in the market. The market share of low-quality crudes is increasing due to the depletion of old fields and increasing demand. This is unnerving the practitioners and affecting the relevance of the traditional benchmark crudes due to the lack of lower quality benchmarks (Montepeque, 2005). In this article, we apply Granger causality tests to study the price dependence of 32 crudes in order to establish which crudes drive other prices and which ones simply follow general market trends. Our results indicate that some of the old benchmarks are still relevant while others can be disregarded. Our results also interestingly show that the low-quality Mediterranean Russian Urals crude, introduced in the late 1990s, has emerged recently as a significant driver of global prices. © 2011 Taylor & Francis.

Information theoretic interpretation of frequency domain connectivity measures

In order to provide adequate multivariate measures of information flow between neural structures, modified expressions of partial directed coherence (PDC) and directed transfer function (DTF), two popular multivariate connectivity measures employed in neuroscience, are introduced and their formal relationship to mutual information rates are proved.

Frequency Domain Connectivity Identification: An Application of Partial Directed Coherence in fMRI

Functional magnetic resonance imaging (fMRI) has become an important tool in Neuroscience due to its noninvasive and high spatial resolution properties compared to other methods like PET or EEG. Characterization of the neural connectivity has been the aim of several cognitive researches, as the interactions among cortical areas lie at the heart of many brain dysfunctions and mental disorders. Several methods like correlation analysis, structural equation modeling, and dynamic causal models have been proposed to quantify connectivity strength. An important concept related to connectivity modeling is Granger causality, which is one of the most popular definitions for the measure of directional dependence between time series. In this article, we propose the application of the partial directed coherence (PDC) for the connectivity analysis of multisubject fMRI data using multivariate bootstrap. PDC is a frequency domain counterpart of Granger causality and has become a very prominent tool in EEG studies. The achieved frequency decomposition of connectivity is useful in separating interactions from neural modules from those originating in scanner noise, breath, and heart beating. Real fMRI dataset of six subjects executing a language processing protocol was used for the analysis of connectivity. Hum Brain Mapp 30:452-461, 2009. (C) 2007 Wiley-Liss, Inc.

Monte Carlo evidence on cointegration and causation

The small sample performance of Granger causality tests under different model dimensions, degree of cointegration, direction of causality, and system stability are presented. Two tests based on maximum likelihood estimation of error-correction models (LR and WALD) are compared to a Wald test based on multivariate least squares estimation of a modified VAR (MWALD). In large samples all test statistics perform well in terms of size and power. For smaller samples, the LR and WALD tests perform better than the MWALD test. Overall, the LR test outperforms the other two in terms of size and power in small samples.

Indicadores avançados para o investimento directo estrangeiro: aplicação ao caso português

RESUMO:O investimento directo estrangeiro tem sido um dos factores com maior importância, no crescimento económico dos países em desenvolvimento, por contribuir para financiar o défice da balança corrente com o exterior, em particular a balança comercial. Num âmbito mais microeconómico é um forte gerador de emprego, proporciona avanços tecnológicos importantes, permitindo a partilha de conhecimentos das tecnologias, o conhecimento de novas formas de gestão e novas formas de marketing. Este trabalho tem como objectivo principal, identificar potenciais variáveis como indicadores avançados para o investimento directo estrangeiro, de modo a antecipar possíveis tendências para a sua evolução. Para alcançar este propósito recorreu-se aos Modelos Autoregressivos Vectoriais (VAR) e à causalidade de Granger com base em dados mensais para o período de Janeiro de 1996 a Setembro de 2010. Foram consideradas variáveis essenvialmente macroeconómicas, tanto do lado da economia receptora como dos países investidores, de modo a reflectirem a actividade económica ao longo do período de estudo. ABSTRACT: The foreign direct investment, has been one of the main factors in the economical development for the countries that are in a process of developing, because it allows the generation of new investments and generate money from the return of the investment, as well as it creates new opportunities for the employment. It allows important technologic advances with the share of the technology Knowledge as well new ways to learn marketing management and enterprise management. This work/research, aims to identify potential variables as advanced indicators for the foreign direct investment, in order to anticipate possible trends of their evolution. To achieve this goal, Vector Autoregressive Models (VAR) and Granger causality based on based on monthly data for the period January between 1996 and September of 2010, were used. Essentially macroeconomic variables were considered, on both the host economy and the countries investors in order to reflect the economic activity throughout the study period.

Estudo sobre o efeito de contágio nos mercados financeiros de acções: aplicação aos índices de acções europeus, americanos, asiáticos e brasileiro no período de Janeiro de 1996 a Junho de 2009 e no sub-período da crise subprime

Mestrado em Contabilidade

Efeito de contágio no mercado financeiro português

Mestrado em Contabilidade e Gestão das Instituições Financeiras

Análise estatística do preço da energia elétrica em mercado livre - Uma aplicação ao caso português

Neste relatório apresentam-se resultados de um estudo estatístico que procura contribuir para um melhor entendimento da problemática inerente à liberalização do setor elétrico em Portugal e dos desafios que esta liberalização, existente desde meados de 2007, trás aos seus intervenientes. Iniciam-se os trabalhos com um estudo que pretende avaliar a existência de relação entre o Preço de Mercado da eletricidade e um conjunto de variáveis potencialmente explicativas/condicionantes do Preço de Mercado. Neste estudo consideram-se duas abordagens. A primeira usa a função de correlação cruzada para avaliar a existência de relação do tipo linear entre pares de variáveis. A segunda considera o teste causalidade de Granger na avaliação de uma relação de causa e efeito entre esses pares. Este estudo avaliou a relação entre o Preço de Mercado da eletricidade e 19 variáveis ditas condicionantes distribuídas por três categorias distintas (consumo e produção de eletricidade; indicadores climáticos; e energias primárias). O intervalo de tempo em estudo cinge-se ao biénio 2012-2103. Durante este período avaliam-se as relações entre as variáveis em diversos sub-períodos de tempo em ciclos de consumo representativos do consumo em baixa (fim de semana) e de consumo mais elevado (fora de vazio) com os valores observados de cada uma das variáveis tratados com uma base horária e diária (média). Os resultados obtidos mostram a existência relação linear entre algumas das variáveis em estudo e o preço da eletricidade em regime de mercado liberalizado, mas raramente é possível identificar precedência temporal entre as variáveis. Considerando os resultados da análise de correlação e causalidade, apresenta-se ainda um modelo de previsão do Preço de Mercado para o curto e médio prazo em horas de período fora de vazio.