ABSTRACT
The need for mining causality, beyond mere statistical correlations, for real world problems has been recognized widely. Many of these applications naturally involve temporal data, which raises the challenge of how best to leverage the temporal information for causal modeling. Recently graphical modeling with the concept of "Granger causality", based on the intuition that a cause helps predict its effects in the future, has gained attention in many domains involving time series data analysis. With the surge of interest in model selection methodologies for regression, such as the Lasso, as practical alternatives to solving structural learning of graphical models, the question arises whether and how to combine these two notions into a practically viable approach for temporal causal modeling. In this paper, we examine a host of related algorithms that, loosely speaking, fall under the category of graphical Granger methods, and characterize their relative performance from multiple viewpoints. Our experiments show, for instance, that the Lasso algorithm exhibits consistent gain over the canonical pairwise graphical Granger method. We also characterize conditions under which these variants of graphical Granger methods perform well in comparison to other benchmark methods. Finally, we apply these methods to a real world data set involving key performance indicators of corporations, and present some concrete results.
Supplemental Material
- T. Chu and C. Glymour. Semi-parametric Causal Inference for Nonlinear Time Series Data. J. of Machine Learning Res., submitted, 2006.Google Scholar
- T. Chu, D. Danks, and C. Glymour. Data Driven Methods for Nonlinear Granger Causality: Climate Teleconnection Mechanisms, 2004.Google Scholar
- D. Coppersmith and S. Winograd. Matrix multiplication via arithmetic progressions. Journal of Symbolic Computation, 9:251280, 1990. Google ScholarDigital Library
- A. Dobra, B. Jones, C. Hans, J. Nevins, M. West. Sparse graphical models for exploring gene expression data. J. of Multivariate Analysis, special issue on Multivariate Methods in Genomic Data Analysis, 90, 196--212, 2003. Google ScholarDigital Library
- M. Drton and M. D. Perlman. A SINful Approach to Gaussian Graphical Model Selection. Department of Statistics, University of Washington, Technical Report 457, 2004.Google Scholar
- B. Efron, T. Hastie, I. Johnstone and R. Tibshirani. Least Angle Regression (with discussion). Annals of Statistics, 2003.Google Scholar
- M. Eichler. Graphical modeling of multivariate time series with latent variables. Preprint, Universiteit Maastricht, 2006.Google Scholar
- N. Friedman, I. Nachman, and D. Peer. Learning Bayesian network structure from massive datasets: The "sparse candidate" algorithm. In (UAI'99), 1999. Google ScholarDigital Library
- P. D. Gilbert. Combining VAR Estimation and State Space Model Reduction for Simple Good Predictions. J. of Forecasting: Special Issue on VAR Modelling, 14:229250, 1995.Google Scholar
- G. Golub, M. Heath, and G. Wahba. Generalized cross validation as a method for choosing a good ridge parameter. Technometrics, 21: 215--224.Google ScholarCross Ref
- C. W. J. Granger. Investigating causal relations by econometric models and cross-spectral methods. Econometrica, 37: 424--438l, 1969.Google ScholarCross Ref
- D. Heckerman. A Tutorial on Learning with Bayesian Networks, In Learning in Graphical Models, M. Jordan, ed., MIT Press, Cambridge, MA, 1999. Google ScholarDigital Library
- P. O. Hoyer, S. Shimizu, and A. J. Kerminen. Estimation of linear, non-gaussian causal models in the presence of confounding latent variables. In (PGM'06), pp. 155--162, 2006.Google Scholar
- M. Kalisch and P. Buehlmann. Estimating high-dimensional directed acyclic graphs with the PC algorithm. Technical report No. 130, ETH Zurich, 2005.Google Scholar
- R. Kaplan and D. Norton. The Balanced Scorecard - Measures that Drive Performance. Harvard Business Review. 71--79, 1992.Google Scholar
- R. Kaplan and D. Norton. The Balanced Scorecard: Translating Strategy into Action. Harvard Business School Press. Boston, MA, 1996.Google Scholar
- S. Lauritzen. Graphical Models. Oxford University Press. 1996.Google Scholar
- C. Meek. Graphical Models: Selecting Causal and Statistical Models. PhD thesis, Carnegie Mellon University, Philosophy Department, 1996.Google Scholar
- N. Meinshausen and P. Buhlmann. High dimensional graphs and variable selection with the Lasso. Annals of Statistics, 34(3), 1436--1462, 2006.Google ScholarCross Ref
- A. Moneta and P. Spirtes. Graphical models for the identification of causal structures in multivariate time series models. In Proc. Fifth Intl. Conf. on Computational Intelligence in Economics and Finance, 2006.Google ScholarCross Ref
- R. Opgen-Rhein and K. Strimmer. Learning causal networks from systems biology time course data: an effective model selection procedure for the vector autoregressive process. BMC Bioinformatics 8 (suppl.) in press, 2007.Google Scholar
- J. Pearl. Causality. Cambridge University Press, Cambridge, UK, 2000.Google Scholar
- S. Roweis and Z. Ghahramani. A Unifying Review of Linear Gaussian Models, Neural Computation, Vol. 11, No. 2, 305--345, 1999. Google ScholarDigital Library
- S. Shimizu, A. Hyvärinen, P. O. Hoyer, and Y. Kano. Finding a causal ordering via independent component analysis. Computational Statistics & Data Analysis, 50(11): 3278--3293, 2006. Google ScholarDigital Library
- R. Silva, R. Scheines, C. Glymour, P. Spirtes. Learning the structure of linear latent variable models. J. of Machine Learning Res., 7(Feb): 191--246, 2006. Google ScholarDigital Library
- P. Spirtes, C. Glymour, and R. Scheines. Causation, Prediction, and Search. MIT Press, New York, NY, second edition, 2000.Google Scholar
- Standard & Poor's Compustat Data. Available from http://www.compustat.com.Google Scholar
- R. Scheines, P. Spirtes, C. Glymour, and C. Meek". TETRAD II: Tools for Discovery. Lawrence Erlbaum Associates, Hillsdale, NJ. 1994.Google Scholar
- R. Tibshirani. Regression shrinkage and selection via the lasso. J. Royal. Statist. Soc B., Vol. 58, No. 1, pages 267--288, 1996.Google Scholar
- P. A. Valdes-Sosa et. al. Estimating brain functional connectivity with sparse multivariate autoregression. Philos Trans R Soc Lond B Biol Sci. 2005 May 29; 360(1457): 969--81, 2005.Google Scholar
Index Terms
- Temporal causal modeling with graphical granger methods
Recommendations
Grouped graphical Granger modeling methods for temporal causal modeling
KDD '09: Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data miningWe develop and evaluate an approach to causal modeling based on time series data, collectively referred to as "grouped graphical Granger modeling methods." Graphical Granger modeling uses graphical modeling techniques on time series data and invokes the ...
Linking granger causality and the pearl causal model with settable systems
NIPSMINI'09: Proceedings of the 12th International Conference on Neural Information Processing Systems (NIPS)Mini-Symposium on Causality in Time SeriesThe causal notions embodied in the concept of Granger causality have been argued to belong to a different category than those of Judea Pearl's Causal Model, and so far their relation has remained obscure. Here, we demonstrate that these concepts are in ...
Deep Stacking Networks for Conditional Nonlinear Granger Causal Modeling of fMRI Data
Machine Learning in Clinical NeuroimagingAbstractConditional Granger causality, based on functional magnetic resonance imaging (fMRI) time series signals, is the quantification of how strongly brain activity in a certain source brain region contributes to brain activity in a target brain region, ...
Comments