Search results for " autoregressive"
showing 10 items of 38 documents
Dynamical model identification of population of oysters for water quality monitoring
2014
International audience; The measurements of valve activity in a population of bivalves under natural environmental conditions (16 oysters in the Bay of Arcachon, France) are used for a physiological model identification. A nonlinear auto-regressive exogenous (NARX) model is designed and tested. The model takes into account the influence of environmental conditions using measurements of the sunlight intensity, the moonlight and tide levels. A possible influence of the internal circadian/circatidal clocks is also analyzed. Through this application, it is demonstrated that the developed dynamical model can be used for estimation of the normal physiological rhythms of permanently immersed oyste…
Categorizing the Role of Respiration in Cardiovascular and Cerebrovascular Variability Interactions
2022
Objective: Respiration disturbs cardiovascular and cerebrovascular controls but its role is not fully elucidated. Methods: Respiration can be classified as a confounder if its observation reduces the strength of the causal relationship from source to target. Respiration is a suppressor if the opposite situation holds. We prove that a confounding/suppression (C/S) test can be accomplished by evaluating the sign of net redundancy/synergy balance in the predictability framework based on multivariate autoregressive modelling. In addition, we suggest that, under the hypothesis of Gaussian processes, the C/S test can be given in the transfer entropy decomposition framework as well. Experimental p…
Testing Frequency-Domain Causality in Multivariate Time Series
2010
We introduce a new hypothesis-testing framework, based on surrogate data generation, to assess in the frequency domain, the concept of causality among multivariate (MV) time series. The approach extends the traditional Fourier transform (FT) method for generating surrogate data in a MV process and adapts it to the specific issue of causality. It generates causal FT (CFT) surrogates with FT modulus taken from the original series, and FT phase taken from a set of series with causal interactions set to zero over the direction of interest and preserved over all other directions. Two different zero-setting procedures, acting on the parameters of a MV autoregressive (MVAR) model fitted on the ori…
Time-Varying Surrogate Data to Assess Nonlinearity in Nonstationary Time Series: Application to Heart Rate Variability
2009
We propose a method to extend to time-varying (TV) systems the procedure for generating typical surrogate time series, in order to test the presence of nonlinear dynamics in potentially nonstationary signals. The method is based on fitting a TV autoregressive (AR) model to the original series and then regressing the model coefficients with random replacements of the model residuals to generate TV AR surrogate series. The proposed surrogate series were used in combination with a TV sample entropy (SE) discriminating statistic to assess nonlinearity in both simulated and experimental time series, in comparison with traditional time-invariant (TIV) surrogates combined with the TIV SE discrimin…
Estimation of Granger causality through Artificial Neural Networks: applications to physiological systems and chaotic electronic oscillators
2021
One of the most challenging problems in the study of complex dynamical systems is to find the statistical interdependencies among the system components. Granger causality (GC) represents one of the most employed approaches, based on modeling the system dynamics with a linear vector autoregressive (VAR) model and on evaluating the information flow between two processes in terms of prediction error variances. In its most advanced setting, GC analysis is performed through a state-space (SS) representation of the VAR model that allows to compute both conditional and unconditional forms of GC by solving only one regression problem. While this problem is typically solved through Ordinary Least Sq…
Assessment of Granger causality by nonlinear model identification: application to short-term cardiovascular variability.
2007
A method for assessing Granger causal relationships in bivariate time series, based on nonlinear autoregressive (NAR) and nonlinear autoregressive exogenous (NARX) models is presented. The method evaluates bilateral interactions between two time series by quantifying the predictability improvement (PI) of the output time series when the dynamics associated with the input time series are included, i.e., moving from NAR to NARX prediction. The NARX model identification was performed by the optimal parameter search (OPS) algorithm, and its results were compared to the least-squares method to determine the most appropriate method to be used for experimental data. The statistical significance of…
Comparative Economic Cycles
2008
The income cycles that have been experienced by six OECD countries over the past 24 years are analysed. The amplitude of the cycles relative to the level of aggregate income varies amongst the countries, as does the degree of the damping that affects the cycles. The study aims to reveal both of these characteristics. It also seeks to determine whether there exists a clear relationship between the degree of damping and the length of the cycles. In order to estimate the parameters of the cycles, the data have been subjected to the processes of detrending, anti-alias filtering and subsampling.
Il Filtro Integrale Auto-Regressivo Continuo (I-ARC) per l’Analisi di Strutture Esposte al Vento
2010
In questo studio viene proposto un metodo per la rappresentazione di processi aleatori Gaussiani e stazionari, utile a modellare la turbolenza della velocità del vento, introducendo la versione integrale del modello auto-regressivo discreto già proposto in precedenza. La rappresentazione di un processo aleatorio di assegnata funzione di correlazione viene condotta integrando un’equazione integro-differenziale in cui viene coinvolto un nucleo, che rappresenta la memoria del processo, in presenza di un rumore bianco Gaussiano. La soluzione dell’equazione rappresenta un campione del processo aleatorio della turbolenza della velocità del vento. E’ stato mostrato che il modello I-ARC fornisce, n…
GDP clustering: A reappraisal
2012
Abstract This note explores clustering in cross country GDP per capita using recently developed model based clustering methods for panel data. Previous research characterizing the components of the overall distribution of output either use ad hoc methods, or methods which ignore/subvert the panel nature of the data. These new methods allow the characterization of the possible autoregressive relationship of output between time points. We show that traditional static clustering decade by decade gives mixed results regarding clustering over time, while the application of longitudinal mixtures presents three distinct clusters at all periods of time.
No linealidad y asimetría en el proceso generador del Índice Ibex35
2013
This paper analyzes the behavior of Ibex35 from January 1999 to December 2001, in order to check if it follows a different process from random walk so its return is not a white noise and it can be predictable, against the efficient market hypothesis. For that, a nonlinear generating process of return will be considered and a STAR-APARCH model will be specified. This model allows a nonlinear behavior in the conditional mean and in the conditional variance. The empirical results show that the Ibex35 follows a nonlinear and asymmetric process, both in the conditional mean as in the conditional variance, so the weak-version of efficient market hypothesis is rejected. El trabajo analiza el compo…