An expectation-maximization algorithm for the matrix normal distribution with an application in remote sensing
From MaRDI portal
Publication:1661328
DOI10.1016/J.JMVA.2018.03.010zbMATH Open1395.62123arXiv1309.6609OpenAlexW2800379364WikidataQ129961530 ScholiaQ129961530MaRDI QIDQ1661328FDOQ1661328
Publication date: 16 August 2018
Published in: Journal of Multivariate Analysis (Search for Journal in Brave)
Abstract: Dramatic increases in the size and dimensionality of many recent data sets make crucial the need for sophisticated methods that can exploit inherent structure and handle missing values. In this article we derive an expectation-maximization (EM) algorithm for the matrix normal distribution, a distribution well-suited for naturally structured data such as spatio-temporal data. We review previously established maximum likelihood matrix normal estimates, and then consider the situation involving missing data. We apply our EM method in a simulation study exploring errors across different dimensions and proportions of missing data. We compare these errors and computational running times to those from two alternative methods. Finally, we implement the proposed EM method on a satellite image dataset to investigate land-cover classification separability.
Full work available at URL: https://arxiv.org/abs/1309.6609
Recommendations
Cites Work
- The mle algorithm for the matrix normal distribution
- Title not available (Why is that?)
- Inference and missing data
- Title not available (Why is that?)
- Some matrix-variate distribution theory: Notational considerations and a Bayesian application
- High-dimensional covariance matrix estimation with missing observations
- Testing for separability of spatial\,-\,temporal covariance functions
- Title not available (Why is that?)
- An asymptotic test for separability of a spatial autoregressive model
- Missing-Data Methods for Generalized Linear Models
- Existence and uniqueness of the maximum likelihood estimator for models with a Kronecker product covariance structure
- Transposable regularized covariance models with an application to missing data imputation
- Models with a Kronecker product covariance structure: estimation and testing
- Missing responses in generalized linear mixed models when the missing data mechanism is nonintegrable
- The origins of kriging
- A Tutorial on the SWEEP Operator
- Analysis of multivariate repeated measures data with a Kronecker product structured covariance matrix
- General class of covariance structures for two or more repeated factors in longitudinal data analysis
- Analysis of multivariate longitudinal data using quasi-least squares
- Scheffés mixed model for multivariate repeated measures:a relative efficiency evaluation
- On discrimination and classification with multivariate repeated measures data
- Robust Kronecker Product PCA for Spatio-Temporal Covariance Estimation
Cited In (9)
- Permutation based testing on covariance separability
- A dual subspace parsimonious mixture of matrix normal distributions
- Estimating high-dimensional covariance and precision matrices under general missing dependence
- Inferring Phenotypic Trait Evolution on Large Trees With Many Incomplete Measurements
- A Legacy of EM Algorithms
- A joint latent factor analyzer and functional subspace model for clustering multivariate functional data
- Mixture of multivariate Gaussian processes for classification of irregularly sampled satellite image time-series
- Existence and uniqueness of the Kronecker covariance MLE
- Clustering of longitudinal interval-valued data via mixture distribution under covariance separability
This page was built for publication: An expectation-maximization algorithm for the matrix normal distribution with an application in remote sensing
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1661328)
