Granger causality and the sampling of economic processes

McCrorie, J. Roderick; Chambers, Marcus J.

doi:10.1016/j.jeconom.2005.02.002

Cited by 55 publications

(49 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Multivariate diffusion models like the ones considered in this paper have been proposed in finance (Sundaresan, 2000), macroeconomics (Bergstrom, 1990;McCrorie and Chambers, 2006), and macro-finance (Piazzesi, 2009).…”

Section: Introductionmentioning

confidence: 99%

Adaptive Lasso-Type Estimation for Multivariate Diffusion Processes

Gregorio¹,

Iacus²

2012

Econom. Theory

View full text Add to dashboard Cite

The least absolute shrinkage and selection operator (LASSO) is a widely used statistical methodology for simultaneous estimation and variable selection. It is a shrinkage estimation method that allows one to select parsimonious models. In other words, this method estimates the redundant parameters as zero in the large samples and reduces variance of estimates. In recent years, many authors analyzed this technique from a theoretical and applied point of view. We introduce and study the adaptive LASSO problem for discretely observed multivariate diffusion processes. We prove oracle properties and also derive the asymptotic distribution of the LASSO estimator. This is a nontrivial extension of previous results by Wang and Leng (2007, Journal of the American Statistical Association, 102(479), 1039-1048) on LASSO estimation because of different rates of convergence of the estimators in the drift and diffusion coefficients. We perform simulations and real data analysis to provide some evidence on the applicability of this method.

show abstract

Section: Introductionmentioning

confidence: 99%

Adaptive Lasso-Type Estimation for Multivariate Diffusion Processes

Gregorio¹,

Iacus²

2012

Econom. Theory

View full text Add to dashboard Cite

show abstract

“…Analyses of the GG approach applied to more general processes, such as neural spiking data (2, 3), continuous-time processes (26), and systems with exogenous inputs and latent variables (4,27), have been shown to produce results inconsistent with the known functional structure of the underlying system. These examples illustrate the perils of applying GG causality in situations where the generative system is poorly approximated by the vector autoregressive (VAR) model class.…”

mentioning

confidence: 99%

A study of problems encountered in Granger causality analysis from a neuroscience perspective

Stokes

Purdon

2017

Proc. Natl. Acad. Sci. U.S.A.

256

189

View full text Add to dashboard Cite

, we misunderstood the method described in Barnett and Seth (25) to compute the conditional Granger causality. We realize now that the spectral factorization method they describe can be used to obtain the conditional Granger causality with a single model fit, which would avoid the computational problems associated with separate model fits. We apologize for this error." Granger causality methods were developed to analyze the flow of information between time series. These methods have become more widely applied in neuroscience. Frequency-domain causality measures, such as those of Geweke, as well as multivariate methods, have particular appeal in neuroscience due to the prevalence of oscillatory phenomena and highly multivariate experimental recordings. Despite its widespread application in many fields, there are ongoing concerns regarding the applicability of Granger causality methods in neuroscience. When are these methods appropriate? How reliably do they recover the system structure underlying the observed data? What do frequency-domain causality measures tell us about the functional properties of oscillatory neural systems? In this paper, we analyze fundamental properties of Granger-Geweke (GG) causality, both computational and conceptual. Specifically, we show that (i) GG causality estimates can be either severely biased or of high variance, both leading to spurious results; (ii) even if estimated correctly, GG causality estimates alone are not interpretable without examining the component behaviors of the system model; and (iii) GG causality ignores critical components of a system's dynamics. Based on this analysis, we find that the notion of causality quantified is incompatible with the objectives of many neuroscience investigations, leading to highly counterintuitive and potentially misleading results. Through the analysis of these problems, we provide important conceptual clarification of GG causality, with implications for other related causality approaches and for the role of causality analyses in neuroscience as a whole.Granger causality | time series analysis | neural oscillations | connectivity | system identification G ranger causality is a statistical tool developed to analyze the flow of information between time series. Neuroscientists have applied Granger causality methods to diverse sources of data, including electroencephalography (EEG), magnetoencephalography (MEG), functional magnetic resonance imaging (fMRI), and local field potentials (LFP). These studies have investigated functional neural systems at scales of organization from the cellular level (1-3) to whole-brain network activity (4), under a range of conditions, including sensory stimuli (5-7), varying levels of consciousness (8-10), cognitive tasks (11), and pathological states (12, 13). In such analyses, the time series data are interpreted to reflect neural activity from a particular source, and Granger causality is used to characterize the directionality, directness, and dynamics of influence between sources.Oscillations are a ...

show abstract

“…Można udowodnić [McCrorie, Chambers, 2006], że jeśli kwartalne obserwacje pewnego procesu są opisane przez model VAR (vector autoregresive), to będą one tożsame z modelem VARMA (o średniej kroczącej o długości 3 okresów) obserwacji danych miesięcznych. Oznacza to, że wpływ agregacji zmiennej po czasie może niekorzystnie wpłynąć na zależności przyczynowe.…”

Section: Wpływ Przekształceń Matematycznych Szeregów Czasowych Na Wynunclassified

O wartości informacyjnej testów przyczynowości w sensie Grangera

Maziarz

2015

Optimum

View full text Add to dashboard Cite

StreszczenieCelem artykułu jest wykazanie na podstawie przeglądu badań, że zastosowanie testów Granger-przyczynowości nie dostarcza wiarygodnych informacji o zależności pomiędzy badanymi szeregami czasowymi, jeżeli nie dysponuje się wiedzą teoretyczną na ich temat. Dotychczasowa krytyka testowania przyczynowości w sensie Grangera skupiała się przede wszystkim na wskazywaniu różnic pomiędzy tradycyjnie rozumianą przyczynowością a definicją zaproponowaną przez Grangera. Autor wykazuje, że analizowana definicja przyczynowości ma uzasadnienie filozoficzne, jednak stosowanie testów Granger-przyczynowości prowadzi do błędnych wniosków, co jest wynikiem m.in.: nieliniowości szeregów czasowych, zbyt rzadkiego próbkowania szeregów czasowych, skointegrowania zmiennych, zdeterminowania szeregów czasowych przez trzecią zmienną, istnienia zależności nieliniowej oraz racjonalnych oczekiwań podmiotów ekonomicznych. Analiza opisanych w literaturze przypadków zawodności wyników testów przyczynowości w sensie Grangera pozwala stwierdzić, że wyciągnięcie wniosków o istnieniu i kierunku zależności przyczynowej na podstawie testu Granger-przyczynowości jest możliwe tylko wtedy, gdy posiada się wiedzę o mechanizmie łączącym dwa szeregi czasowe.Słowa kluczowe: przyczynowość w sensie Grangera, testowanie przyczynowości, przyczynowość w ekonomii ON INFORMATIVENESS OF GRANGER-CAUSALITY TESTS SummaryThe purpose of this paper is to show that the application of Granger-causality tests is not informative unless one possesses additional theoretical knowledge. Previous criticism on Granger-causality testing pointed out mostly the differences between the common sense understanding of causality and Granger's definition. The author demonstrates that Granger's definition of causality is philosophically justified. However, the use of its tests is misleading due to: data non-linearity, too low sampling rate, time series cointegration, thirdvariable fallacy, non-linear causal dependency, and the rational expectations of economic agents. It can be said that the fallibility of Granger-causality testing described in the literature makes drawing conclusions about the existence and direction of causal relationship possible only if the researcher applying a Grangercausality test has knowledge of the mechanism connecting the two time series.

show abstract

Granger causality and the sampling of economic processes

Cited by 55 publications

References 37 publications

Adaptive Lasso-Type Estimation for Multivariate Diffusion Processes

Adaptive Lasso-Type Estimation for Multivariate Diffusion Processes

A study of problems encountered in Granger causality analysis from a neuroscience perspective

O wartości informacyjnej testów przyczynowości w sensie Grangera

Contact Info

Product

Resources

About