Identifiability of latent-variable and structural-equation models: from linear to nonlinear
From MaRDI portal
Abstract: An old problem in multivariate statistics is that linear Gaussian models are often unidentifiable, i.e. some parameters cannot be uniquely estimated. In factor (component) analysis, an orthogonal rotation of the factors is unidentifiable, while in linear regression, the direction of effect cannot be identified. For such linear models, non-Gaussianity of the (latent) variables has been shown to provide identifiability. In the case of factor analysis, this leads to independent component analysis, while in the case of the direction of effect, non-Gaussian versions of structural equation modelling solve the problem. More recently, we have shown how even general nonparametric nonlinear versions of such models can be estimated. Non-Gaussianity is not enough in this case, but assuming we have time series, or that the distributions are suitably modulated by some observed auxiliary variables, the models are identifiable. This paper reviews the identifiability theory for the linear and nonlinear cases, considering both factor analytic models and structural equation models.
Cites work
- scientific article; zbMATH DE number 6378135 (Why is no real title available?)
- scientific article; zbMATH DE number 3164189 (Why is no real title available?)
- scientific article; zbMATH DE number 45532 (Why is no real title available?)
- scientific article; zbMATH DE number 7306898 (Why is no real title available?)
- scientific article; zbMATH DE number 3227988 (Why is no real title available?)
- scientific article; zbMATH DE number 3258737 (Why is no real title available?)
- A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction
- A linear non-Gaussian acyclic model for causal discovery
- An extension of slow feature analysis for nonlinear blind source separation
- Blind separation of instantaneous mixtures of nonstationary sources
- Blind separation of mixture of independent sources through a quasi-maximum likelihood approach
- Blind separation of sources. I: An adaptive algorithm based on neuromimetic architecture
- Causality. Models, reasoning, and inference
- DirectLiNGAM: a direct method for learning a linear non-Gaussian structural equation model
- Elements of causal inference. Foundations and learning algorithms
- Estimation of causal effects using linear non-Gaussian causal models with hidden variables
- Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data
- Identifiability of Gaussian structural equation models with equal error variances
- Independent component analysis, a new concept?
- Indeterminacy and identifiability of blind identification
- Kernel-Based Nonlinear Blind Source Separation
- Learning the parts of objects by non-negative matrix factorization
- Minimal nonlinear distortion principle for nonlinear independent component analysis
- Natural image statistics. A probabilistic approach to early computational vision.
- Non-negative matrix factorization with sparseness constraints
- Nonlinear independent component analysis for discrete-time and continuous-time signals
- Pairwise likelihood ratios for estimation of non-Gaussian structural equation models
- ParceLiNGAM: a causal ordering method robust against latent confounders
- Performance analysis of the FastICA algorithm and Crame/spl acute/r-rao bounds for linear independent component analysis
Cited in
(2)
This page was built for publication: Identifiability of latent-variable and structural-equation models: from linear to nonlinear
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6138746)
