Abstract
An effective way to examine causality is to conduct an experiment with random assignment. However, in many cases it is impossible or too expensive to perform controlled experiments, and hence one often has to resort to methods for discovering good initial causal models from data which do not come from such controlled experiments. We have recently proposed such a discovery method based on independent component analysis (ICA) called LiNGAM and shown how to completely identify the data generating process under the assumptions of linearity, non-gaussianity, and no latent variables. In this paper, after briefly recapitulating this approach, we extend the framework to cases where latent classes (hidden groups) are present. The model identification can be accomplished using a method based on ICA mixtures. Simulations confirm the validity of the proposed method.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Holland, P.W.: Statistics and causal inference (with discussion). Journal of the American Statistical Association 81, 945–970 (1986)
Bollen, K.A.: Structural Equations with Latent Variables. John Wiley & Sons, Chichester (1989)
Imoto, S., Goto, T., Miyano, S.: Estimation of genetic networks and functional structures between genes by using Bayesian network and nonparametric regression. In: Proc. Pacific Symposium on Biocomputing, vol. 7, pp. 175–186 (2002)
Kim, J., Zhu, W., Chang, L., Bentler, P.M., Ernst, T.: Unified structural equation modeling approach for the analysis of multisubject, multivariate functional MRI data. Human Brain Mapping 28, 85–93 (2007)
Pearl, J.: Causality: Models, Reasoning, and Inference. Cambridge University Press, Cambridge (2000)
Spirtes, P., Glymour, C., Scheines, R.: Causation, Prediction, and Search, 2nd edn. MIT Press, Cambridge (2000)
Shimizu, S., Kano, Y.: Use of non-normality in structural equation modeling: Application to direction of causation. Journal of Statistical Planning and Inference (in press, 2006)
Shimizu, S., Hyvärinen, A., Hoyer, P.O., Kano, Y.: Finding a causal ordering via independent component analysis. Computational Statistics & Data Analysis 50(11), 3278–3293 (2006)
Shimizu, S., Hoyer, P.O., Hyvärinen, A., Kerminen, A.: A linear non-gaussian acyclic model for causal discovery. J. of Machine Learning Research 7, 2003–2030 (2006)
Comon, P.: Independent component analysis. a new concept? Signal Processing 36, 62–83 (1994)
Hyvärinen, A., Karhunen, J., Oja, E.: Independent component analysis. Wiley, New York (2001)
Tanner, J., Israelsohn, W.: Parent-child correlation for body measurements of children between the ages one month and seven years. Ann.Hum.Genet. 26, 245–259 (1963)
Lee, T.W., Lewicki, M., Sejnowski, T.: ICA mixture models for unsupervised classification of non-gaussian sources and automatic context switching in blind signal separation. IEEE Trans. on Pattern Recognition and Machine Intelligence 22(10), 1–12 (2000)
Mollah, M.N.H., Minami, M., Eguchi, S.: Exploring latent structure of mixture ICA models by the minimum β-divergence method. Neural Computation 18, 166–190 (2006)
Minami, M., Eguchi, S.: Adaptive selection for minimum β-divergence method. In: Proc. the Fourth Int. Conf. on Independent Component Analysis and Blind Signal Separation (ICA 2003), Nara, Japan, pp. 475–480 (2003)
Pham, D.T., Garrat, P.: Blind separation of mixture of independent sources through a quasi-maximum likelihood approach. Signal Processing 45, 1457–1482 (1997)
Muthén, B.O.: Beyond SEM: General latent variables modeling. Behaviormetrika 29, 81–117 (2002)
Hoyer, P.O., Shimizu, S., Kerminen, A.: Estimation of linear, non-gaussian causal models in the presence of confounding latent variables. In: Proc. the third European Workshop on Probabilistic Graphical Models (PGM2006), pp. 155–162 (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Shimizu, S., Hyvärinen, A. (2008). Discovery of Linear Non-Gaussian Acyclic Models in the Presence of Latent Classes. In: Ishikawa, M., Doya, K., Miyamoto, H., Yamakawa, T. (eds) Neural Information Processing. ICONIP 2007. Lecture Notes in Computer Science, vol 4984. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69158-7_78
Download citation
DOI: https://doi.org/10.1007/978-3-540-69158-7_78
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69154-9
Online ISBN: 978-3-540-69158-7
eBook Packages: Computer ScienceComputer Science (R0)