Learning multivariate time series causal graphs based on conditional mutual information

Abstract

Detection and clarification of cause-effect relationships among variables is an important problem in time series analysis. This paper provides a method that employs both mutual information and conditional mutual information to identify the causal structure of multivariate time series causal graphical models. A three-step procedure is developed to learn the contemporaneous and the lagged causal relationships of time series causal graphs. Contrary to conventional constraint-based algorithm, the proposed algorithm does not involve any special kinds of distribution and is nonparametric. These properties are especially appealing for inference of time series causal graphs when the prior knowledge about the data model is not available. Simulations and case analysis demonstrate the effectiveness of the method.

Keywords

Multivariate time series / causal graphs / conditional independence / conditional mutual information

References

[1] Bach F.R., Jordan M.I.. Learning graphical models for stationary time series. IEEE Transactions on signal processing, 2004, 52: 2189-2199.

[2] Barnes J.A., Sargent H.H., Tryon P.V.. Pepin R.O., Eddy J.A., Merrill R.B.. Sunspot cycle simulation using random noise. The Ancient Sun, 1980, New York: Pergamon 159-163.

[3] Butte A.J., Kohane I.S.. Mutual information relevance networks: functional genomic clustering using pairwise entropy measurements. Pacsymp Biocompt, 2000, 6: 418-429.

[4] Carvalho C.M., West M.. Dynamic matrix-variate graphical models. Bayesian Analysis, 2007, 2: 69-98.

[5] Chen, P. & Hsiao, C. (2007). Learning causal relations in multivariate time series data. Economics ejournal, Discussion Paper, 2007-15

[6] Dahlhaus R.. Graphical interaction models for multivariate time series. Metrika, 2000, 51: 157-172.

[7] Daub C., Steuer R., Selbig J., Kloska S.. Estimating mutual information using B-spline functions — an improved similarity measure for analysing gene expression data. BMC Bioinformatics, 2004, 5: 1-12.

[8] Eichler M.. Granger causality and path diagrams for multivariate time series. Journal of Econometrics, 2007, 137: 334-353.

[9] Gao W., Tian Z.. Learning Granger causality graphs for multivariate nonlinear time series. Journal of Systems Science and Systems Engineering, 2009, 18(1): 38-52.

[10] Goria M., Leonenko N., Mergel V., Inverardi P.N.. A new class of random vector entropy estimators and its applications in testing statistical hypotheses. Journal of Nonparametric Statistics, 2005, 17: 277-298.

[11] Grassberger P., Procaccia I.. Estimation of Kolmogorov entropy from a chaotic signal. Physical Review A, 1983, 28: 2591-2593.

[12] Hall P., Morton S.C.. On the estimation of entropy. Annals of the Institute of Statistical Mathematics, 1993, 45: 69-88.

[13] Hoover K.. Automatic inference of the contemporaneous causal order of a system of equations. Econometric Theory, 2005, 21: 69-77.

[14] Hyvärinen A., Zhang K., Shimizu S., Hoyer P.O.. Estimation of a structural vector autoregression model using non-Gaussianity. Journal of Machine Learning Research, 2010, 11: 1709-1731.

[15] Knuth, K.H., Gotera, A., Curry, K.A., Wheeler, K.R. & Rossow, W.B. (2005). Revealing relationships among relevant climate variables with information theroy. Paper presented at Earth-Sun System Technology Conference, Adelphi, MD, 2005

[16] Margolin A., Nemenman I., Basso K.. ARANCE: an algorithm for the reconstruction of gene regulatory networks in a mammalian cellular context. BMC Bioinformatics, 2006, 7: 1-15.

[17] Marschinski R., Kantz H.. Analysing the information flow between financial time series-an improved estimator for transfer entropy. European Physical Journal B, 2002, 30: 275-281.

[18] Moneta A.. Graphical causal models and VARs: an empirical assessment of the real business cycles hypothesis. Empire Economics, 2008, 35: 275-300.

[19] Oxley L., Reale M., Wilson G.. Constructing structural VAR models with conditional independence graphs. Mathematics and Computers in Simulation, 2009, 79: 2910-2916.

[20] Olbrich E., Kantz H.. Inferring chaotic dynamics from time series: on which length scale determinism becomes visible. Physics Letters A, 1997, 45(10): 7058-7064.

[21] Pulas M.. Testing for nonlinearity using redundancies: quantitative and qualitative aspects. Physica D, 1995, 80: 186-205.

[22] Pearl J.. Causality: Models, Reasoning and Inference, 2000, Cambridge: Cambridge University Press.

[23] Prichard D., Theiler J.. Generalized redundancies for time series analysis. Physica D, 1995, 84: 476-493.

[24] Spirtes P., Glymour C., Scheines R.. Causation, Prediction and Search, 2001, New York: Springr-Verlag.

[25] Spirtes P., Glymour C.. An algorithm for fast recovery of sparse causal graphs. Social Science Computer Review, 1991, 9: 67-72.

[26] Vejmelka M., Palus M.. Inferring the directionality of coupling with conditional mutual information. Physical Review E, 2008, 77: 1-12.