Download:
by Shohei Shimizu, Patrik O. Hoyer, Aapo Hyvärinen, Antti Kerminen
Journal of Machine Learning Research
http://www.jmlr.org/papers/volume7/shimizu06a/shimizu06a.pdf
Add To MetaCart
Abstract:
In recent years, several methods have been proposed for the discovery of causal structure from non-experimental data. Such methods make various assumptions on the data generating process to facilitate its identification from purely observational data. Continuing this line of research, we show how to discover the complete causal structure of continuous-valued data, under the assumptions that (a) the data generating process is linear, (b) there are no unobserved confounders, and (c) disturbance variables have non-Gaussian distributions of non-zero variances. The solution relies on the use of the statistical method known as independent component analysis, and does not require any pre-specified time-ordering of the variables. We provide a complete Matlab package for performing this LiNGAM analysis (short for Linear Non-Gaussian Acyclic Model), and demonstrate the effectiveness of the method using artificially generated data and real-world data.
Citations
|
1109
|
An Introduction to the Bootstrap
– EFRON, J
- 1993
|
|
835
|
Independent component analysis: A new concept
– Comon
- 1994
|
|
734
|
Reinsel, Time Series Analysis: Forecasting and Control (Third Edition
– Box, Jenkins, et al.
- 1994
|
|
402
|
Controlling the false discovery rate: A practical and powerful approach to multiple testing
– Benjamini, Hochberg
- 1995
|
|
378
|
Causality: models, reasoning, and inference
– Pearl
- 2000
|
|
287
|
Equivariant adaptive source separation
– Cardoso, Laheld
- 1996
|
|
281
|
Time Series: Theory and Methods
– BROCKWELL, R
- 1991
|
|
276
|
Blind beamforming for non-Gaussian signals
– Cardoso, Souloumiac
- 1993
|
|
221
|
Fast and robust fixed-point algorithms for independent component analysis
– Hyvarinen
- 1999
|
|
188
|
Structural Equations with Latent Variables
– Bollen
- 1989
|
|
72
|
A simple sequentially rejective multiple test procedure
– Holm
- 1979
|
|
72
|
Blind separation of a mixture of independent sources through a quasi-maximum likelihood approach
– Pham, Garrat
- 1997
|
|
71
|
Learning Gaussian networks
– Geiger, Heckerman
- 1994
|
|
62
|
Tamhane, Multiple Comparison Procedures
– Hochberg, C
- 1987
|
|
28
|
A sharper Bonferroni procedure for multiple tests of significance
– Hochberg
- 1988
|
|
23
|
Estimating Functions
– Godambe
- 1991
|
|
23
|
An improved Bonferroni procedure for multiple tests of significance
– Simes
- 1986
|
|
18
|
On the quality of test statistics in covariance structure analysis: Caveat emptor
– Bentler
- 1994
|
|
16
|
Linear assignment problems and extensions
– Burkard, Cela
- 1999
|
|
7
|
Validating the independent components of neuroimaging time series via clustering and visualization
– Himberg, Hyvärinen, et al.
- 2004
|
|
6
|
Finding a causal ordering via independent component analysis
– Shimizu, Hyvärinen, et al.
- 2006
|
|
5
|
A.: Estimation of linear, non-gaussian causal models in the presence of confounding latent variables
– Hoyer, Shimizu, et al.
- 2006
|
|
3
|
Discovery of non-gaussian linear causal models using ICA
– Shimizu, Hyvärinen, et al.
- 2005
|
|
3
|
Use of non-normality in structural equation modeling: Application to direction of causation
– Shimizu, Kano
|
|
3
|
Performance analysis of the FastICA algorithm and Cramèr-Rao bounds for linear independent component analysis
– Tichavsk´y, Koldovsk´y, et al.
|
|
2
|
On asymptotic properties of the correlation coefficient in the regression setting
– Dodge, Rousson
|
|
2
|
New permutation algorithms for causal discovery using ICA
– Hoyer, Shimizu, et al.
- 2006
|
|
2
|
Time series data library, 2005. URL http://www-personal.buseco.monash. edu.au/˜hyndman/TSDL/. [June 2005]. A. Hyvärinen. One-unit contrast functions for independent component analysis: A statistical analysis
– Hyndman
|
|
2
|
Testing significance of mixing and demixing coefficients in ICA
– Shimizu, Hyvärinen, et al.
|
|
1
|
Estimating functions for blind separation when sources have variance dependencies
– SHIMIZU, HYVÄRINEN, et al.
|
