Detecting Causality by Combined Use of Multiple Methods: Climate and Brain Examples

Solar activity facilitates daily forecasts of large earthquakes

Despite the extensive literature related to earthquakes, an effective method to forecast and avoid occasional seismic hazards that cause substantial damage is lacking. The Sun has recently been identified as a potential precursor to earthquakes, although no causal relationship between its activity and the Earth's seismicity has been established. This study was aimed at investigating whether such a relationship exists and whether it can be used to improve earthquake forecasting. The edit distances between earthquake point processes were combined with delay-coordinate distances for sunspot numbers. The comparison of these two indicated the existence of unidirectional causal coupling from solar activity to seismicity on Earth, and a radial basis function regressor showed accuracy improvements in the largest magnitude prediction of next days by 2.6%-17.9% in the odds ratio when sunspot distances were included.

Fast and effective pseudo transfer entropy for bivariate data-driven causal inference

Identifying, from time series analysis, reliable indicators of causal relationships is essential for many disciplines. Main challenges are distinguishing correlation from causality and discriminating between direct and indirect interactions. Over the years many methods for data-driven causal inference have been proposed; however, their success largely depends on the characteristics of the system under investigation. Often, their data requirements, computational cost or number of parameters limit their applicability. Here we propose a computationally efficient measure for causality testing, which we refer to as pseudo transfer entropy (pTE), that we derive from the standard definition of transfer entropy (TE) by using a Gaussian approximation. We demonstrate the power of the pTE measure on simulated and on real-world data. In all cases we find that pTE returns results that are very similar to those returned by Granger causality (GC). Importantly, for short time series, pTE combined with time-shifted (T-S) surrogates for significance testing strongly reduces the computational cost with respect to the widely used iterative amplitude adjusted Fourier transform (IAAFT) surrogate testing. For example, for time series of 100 data points, pTE and T-S reduce the computational time by \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$82\%$$\end{document}82% with respect to GC and IAAFT. We also show that pTE is robust against observational noise. Therefore, we argue that the causal inference approach proposed here will be extremely valuable when causality networks need to be inferred from the analysis of a large number of short time series.

The Human Organism as an Integrated Interaction Network: Recent Conceptual and Methodological Challenges

The field of Network Physiology aims to advance our understanding of how physiological systems and sub-systems interact to generate a variety of behaviors and distinct physiological states, to optimize the organism's functioning, and to maintain health. Within this framework, which considers the human organism as an integrated network, vertices are associated with organs while edges represent time-varying interactions between vertices. Likewise, vertices may represent networks on smaller spatial scales leading to a complex mixture of interacting homogeneous and inhomogeneous networks of networks. Lacking adequate analytic tools and a theoretical framework to probe interactions within and among diverse physiological systems, current approaches focus on inferring properties of time-varying interactions-namely strength, direction, and functional form-from time-locked recordings of physiological observables. To this end, a variety of bivariate or, in general, multivariate time-series-analysis techniques, which are derived from diverse mathematical and physical concepts, are employed and the resulting time-dependent networks can then be further characterized with methods from network theory. Despite the many promising new developments, there are still problems that evade from a satisfactory solution. Here we address several important challenges that could aid in finding new perspectives and inspire the development of theoretic and analytical concepts to deal with these challenges and in studying the complex interactions between physiological systems.

Partial cross mapping eliminates indirect causal influences

Causality detection likely misidentifies indirect causations as direct ones, due to the effect of causation transitivity. Although several methods in traditional frameworks have been proposed to avoid such misinterpretations, there still is a lack of feasible methods for identifying direct causations from indirect ones in the challenging situation where the variables of the underlying dynamical system are non-separable and weakly or moderately interacting. Here, we solve this problem by developing a data-based, model-independent method of partial cross mapping based on an articulated integration of three tools from nonlinear dynamics and statistics: phase-space reconstruction, mutual cross mapping, and partial correlation. We demonstrate our method by using data from different representative models and real-world systems. As direct causations are keys to the fundamental underpinnings of a variety of complex dynamics, we anticipate our method to be indispensable in unlocking and deciphering the inner mechanisms of real systems in diverse disciplines from data.

It is crucial yet challenging to identify cause-consequence relation in complex dynamical systems where direct causal links can mix with indirect ones. Leng et al. propose a data-driven model-independent method to distinguish direct from indirect causality and test its applicability to real-world data.

Detecting and quantifying causal associations in large nonlinear time series datasets

Identifying causal relationships and quantifying their strength from observational time series data are key problems in disciplines dealing with complex dynamical systems such as the Earth system or the human body. Data-driven causal inference in such systems is challenging since datasets are often high dimensional and nonlinear with limited sample sizes. Here, we introduce a novel method that flexibly combines linear or nonlinear conditional independence tests with a causal discovery algorithm to estimate causal networks from large-scale time series datasets. We validate the method on time series of well-understood physical mechanisms in the climate system and the human heart and using large-scale synthetic datasets mimicking the typical properties of real-world data. The experiments demonstrate that our method outperforms state-of-the-art techniques in detection power, which opens up entirely new possibilities to discover and quantify causal networks from time series across a range of research fields.

Causality detection in cortical seizure dynamics using cross-dynamical delay differential analysis

Most natural systems, including the brain, are highly nonlinear and complex, and determining information flow among the components that make up these dynamic systems is challenging. One such example is identifying abnormal causal interactions among different brain areas that give rise to epileptic activities. Here, we introduce cross-dynamical delay differential analysis, an extension of delay differential analysis, as a tool to establish causal relationships from time series signals. Our method can infer causality from short time series signals as well as in the presence of noise. Furthermore, we can determine the onset of generalized synchronization directly from time series data, without having to consult the underlying equations. We first validate our method on simulated datasets from coupled dynamical systems and apply the method to intracranial electroencephalography data obtained from epilepsy patients to better characterize large-scale information flow during epilepsy.

Reconstructing directional causal networks with random forest: Causality meeting machine learning

Inspired by the decision tree algorithm in machine learning, a novel causal network reconstruction framework is proposed with the name Importance Causal Analysis (ICA). The ICA framework is designed in a network level and fills the gap between traditional mutual causality detection methods and the reconstruction of causal networks. The potential of the method to identify the true causal relations in complex networks is validated by both benchmark systems and real-world data sets.

Surrogate Data Preserving All the Properties of Ordinal Patterns up to a Certain Length

We propose a method for generating surrogate data that preserves all the properties of ordinal patterns up to a certain length, such as the numbers of allowed/forbidden ordinal patterns and transition likelihoods from ordinal patterns into others. The null hypothesis is that the details of the underlying dynamics do not matter beyond the refinements of ordinal patterns finer than a predefined length. The proposed surrogate data help construct a test of determinism that is free from the common linearity assumption for a null-hypothesis.

Inferring causation from time series in Earth system sciences

The heart of the scientific enterprise is a rational effort to understand the causes behind the phenomena we observe. In large-scale complex dynamical systems such as the Earth system, real experiments are rarely feasible. However, a rapidly increasing amount of observational and simulated data opens up the use of novel data-driven causal methods beyond the commonly adopted correlation techniques. Here, we give an overview of causal inference frameworks and identify promising generic application cases common in Earth system sciences and beyond. We discuss challenges and initiate the benchmark platform causeme.net to close the gap between method users and developers.

Brain Network Changes in Fatigued Drivers: A Longitudinal Study in a Real-World Environment Based on the Effective Connectivity Analysis and Actigraphy Data

The analysis of neurophysiological changes during driving can clarify the mechanisms of fatigue, considered an important cause of vehicle accidents. The fluctuations in alertness can be investigated as changes in the brain network connections, reflected in the direction and magnitude of the information transferred. Those changes are induced not only by the time on task but also by the quality of sleep. In an unprecedented 5-month longitudinal study, daily sampling actigraphy and EEG data were collected during a sustained-attention driving task within a near-real-world environment. Using a performance index associated with the subjects' reaction times and a predictive score related to the sleep quality, we identify fatigue levels in drivers and investigate the shifts in their effective connectivity in different frequency bands, through the analysis of the dynamical coupling between brain areas. Study results support the hypothesis that combining EEG, behavioral and actigraphy data can reveal new features of the decline in alertness. In addition, the use of directed measures such as the Convergent Cross Mapping can contribute to the development of fatigue countermeasure devices.

Comparing brain connectivity metrics: a didactic tutorial with a toy model and experimental data

OBJECTIVE

The objective of this paper is to didactically compare resting state connectivity networks computed using two different methods called phase locking value (PLV) and convergent cross-mapping (CCM). PLV is a ubiquitous measure of connectivity in electrophysiological research but is less often applied to fMRI BOLD timeseries since this model-based metric assumes that oscillatory coupling is a sufficient condition for connectivity. Alternatively, CCM is a model-free method, which detects potentially nonlinear causal influences based on the ability to estimate one timeseries with another and does not assume an oscillatory structure.

APPROACH

We use a toy dataset to test the PLV and CCM algorithms under different known synchronization conditions. Additionally, experimental resting state EEG and fMRI datasets are used for comparison.

MAIN RESULTS

The results show that the resting state brain networks computed using both algorithms produce similar results for both resting state EEG and fMRI datasets. For both neuroimaging datasets, the network characteristics follow the same trends and the similarity between the computed networks, for both algorithms, is highly significant.

SIGNIFICANCE

CCM is able to identify low or one-way connection strengths better than PLV but takes exponentially longer to compute. Based on these results, PLV provides a good metric for on-line network identification because it is both computationally fast and an excellent approximation of the network computed with CCM.

Exploiting nonlinearity of the speech production system for voice disorder assessment by recurrence quantification analysis

This work summarizes the research related to digital speech signal processing with recurrence quantification analysis (RQA) applied to voice disorder assessment. The main motivation for these studies is the fact that RQA is able to exploit the nonlinear dynamical nature of the speech production system. Due to the use of recurrence quantification measures to represent the behavior of speech signals, promising results were obtained in the characterization and classification of laryngeal pathologies and voice disorders. These contributions may help one to evaluate the usability and efficiency of RQA in vocal disorder assessment.

Detecting directional couplings from multivariate flows by the joint distance distribution

The identification of directional couplings (or drive-response relationships) in the analysis of interacting nonlinear systems is an important piece of information to understand their dynamics. This task is especially challenging when the analyst's knowledge of the systems reduces virtually to time series of observations. Spurred by the success of Granger causality in econometrics, the study of cause-effect relationships (not to be confounded with statistical correlations) was extended to other fields, thus favoring the introduction of further tools such as transfer entropy. Currently, the research on old and new causality tools along with their pitfalls and applications in ever more general situations is going through a time of much activity. In this paper, we re-examine the method of the joint distance distribution to detect directional couplings between two multivariate flows. This method is based on the forced Takens theorem, and, more specifically, it exploits the existence of a continuous mapping from the reconstructed attractor of the response system to the reconstructed attractor of the driving system, an approach that is increasingly drawing the attention of the data analysts. The numerical results with Lorenz and Rössler oscillators in three different interaction networks (including hidden common drivers) are quite satisfactory, except when phase synchronization sets in. They also show that the method of the joint distance distribution outperforms the lowest dimensional transfer entropy in the cases considered. The robustness of the results to the sampling interval, time series length, observational noise, and metric is analyzed too.

Detecting causality using symmetry transformations

Detecting causality between variables in a time series is a challenge, particularly when the relationship is nonlinear and the dataset is noisy. Here, we present a novel tool for detecting causality that leverages the properties of symmetry transformations. The aim is to develop an algorithm with the potential to detect both unidirectional and bidirectional coupling for nonlinear systems in the presence of significant sampling noise. Most of the existing tools for detecting causality can make determinations of directionality, but those determinations are relatively fragile in the presence of noise. The novel algorithm developed in the present study is robust and very conservative in that it reliably detects causal structure with a very low rate of error even in the presence of high sampling noise. We demonstrate the performance of our algorithm and compare it with two popular model-free methods, namely transfer entropy and convergent cross map. This first implementation of the method of symmetry transformations is limited in that it applies only to first-order autonomous systems.

Introduction to Focus Issue: Causation inference and information flow in dynamical systems: Theory and applications

Questions of causation are foundational across science and often relate further to problems of control, policy decisions, and forecasts. In nonlinear dynamics and complex systems science, causation inference and information flow are closely related concepts, whereby "information" or knowledge of certain states can be thought of as coupling influence onto the future states of other processes in a complex system. While causation inference and information flow are by now classical topics, incorporating methods from statistics and time series analysis, information theory, dynamical systems, and statistical mechanics, to name a few, there remain important advancements in continuing to strengthen the theory, and pushing the context of applications, especially with the ever-increasing abundance of data collected across many fields and systems. This Focus Issue considers different aspects of these questions, both in terms of founding theory and several topical applications.

Causal network reconstruction from time series: From theoretical assumptions to practical estimation

Causal network reconstruction from time series is an emerging topic in many fields of science. Beyond inferring directionality between two time series, the goal of causal network reconstruction or causal discovery is to distinguish direct from indirect dependencies and common drivers among multiple time series. Here, the problem of inferring causal networks including time lags from multivariate time series is recapitulated from the underlying causal assumptions to practical estimation problems. Each aspect is illustrated with simple examples including unobserved variables, sampling issues, determinism, stationarity, nonlinearity, measurement error, and significance testing. The effects of dynamical noise, autocorrelation, and high dimensionality are highlighted in comparison studies of common causal reconstruction methods. Finally, method performance evaluation approaches and criteria are suggested. The article is intended to briefly review and accessibly illustrate the foundations and practical problems of time series-based causal discovery and stimulate further methodological developments.

Dimensionless embedding for nonlinear time series analysis

Recently, infinite-dimensional delay coordinates (InDDeCs) have been proposed for predicting high-dimensional dynamics instead of conventional delay coordinates. Although InDDeCs can realize faster computation and more accurate short-term prediction, it is still not well-known whether InDDeCs can be used in other applications of nonlinear time series analysis in which reconstruction is needed for the underlying dynamics from a scalar time series generated from a dynamical system. Here, we give theoretical support for justifying the use of InDDeCs and provide numerical examples to show that InDDeCs can be used for various applications for obtaining the recurrence plots, correlation dimensions, and maximal Lyapunov exponents, as well as testing directional couplings and extracting slow-driving forces. We demonstrate performance of the InDDeCs using the weather data. Thus, InDDeCs can eventually realize "dimensionless embedding" while we enjoy faster and more reliable computations.

Assessment of resampling methods for causality testing: A note on the US inflation behavior

Different resampling methods for the null hypothesis of no Granger causality are assessed in the setting of multivariate time series, taking into account that the driving-response coupling is conditioned on the other observed variables. As appropriate test statistic for this setting, the partial transfer entropy (PTE), an information and model-free measure, is used. Two resampling techniques, time-shifted surrogates and the stationary bootstrap, are combined with three independence settings (giving a total of six resampling methods), all approximating the null hypothesis of no Granger causality. In these three settings, the level of dependence is changed, while the conditioning variables remain intact. The empirical null distribution of the PTE, as the surrogate and bootstrapped time series become more independent, is examined along with the size and power of the respective tests. Additionally, we consider a seventh resampling method by contemporaneously resampling the driving and the response time series using the stationary bootstrap. Although this case does not comply with the no causality hypothesis, one can obtain an accurate sampling distribution for the mean of the test statistic since its value is zero under H₀. Results indicate that as the resampling setting gets more independent, the test becomes more conservative. Finally, we conclude with a real application. More specifically, we investigate the causal links among the growth rates for the US CPI, money supply and crude oil. Based on the PTE and the seven resampling methods, we consistently find that changes in crude oil cause inflation conditioning on money supply in the post-1986 period. However this relationship cannot be explained on the basis of traditional cost-push mechanisms.

Computing algebraic transfer entropy and coupling directions via transcripts

Most random processes studied in nonlinear time series analysis take values on sets endowed with a group structure, e.g., the real and rational numbers, and the integers. This fact allows to associate with each pair of group elements a third element, called their transcript, which is defined as the product of the second element in the pair times the first one. The transfer entropy of two such processes is called algebraic transfer entropy. It measures the information transferred between two coupled processes whose values belong to a group. In this paper, we show that, subject to one constraint, the algebraic transfer entropy matches the (in general, conditional) mutual information of certain transcripts with one variable less. This property has interesting practical applications, especially to the analysis of short time series. We also derive weak conditions for the 3-dimensional algebraic transfer entropy to yield the same coupling direction as the corresponding mutual information of transcripts. A related issue concerns the use of mutual information of transcripts to determine coupling directions in cases where the conditions just mentioned are not fulfilled. We checked the latter possibility in the lowest dimensional case with numerical simulations and cardiovascular data, and obtained positive results.