Forward adaptive banding for estimating large covariance matrices
- 30 September 2011
- journal article
- research article
- Published by Oxford University Press (OUP) in Biometrika
- Vol. 98 (4) , 821-830
Abstract
We propose a simple forward adaptive banding method for estimating large covariance matrices using the modified Cholesky decomposition. This approach requires the fitting of a prespecified set of models due to the adaptive banding structure and can be efficiently implemented. Aside from its computational attractiveness, we propose a novel Bayes information criterion that gives consistent model selection for estimating high dimensional covariance matrices. The method compares favourably to its competitors in simulation study.Keywords
This publication has 11 references indexed in Scilit:
- Sparsistency and rates of convergence in large covariance matrix estimationThe Annals of Statistics, 2009
- Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using $\ell _{1}$-Constrained Quadratic Programming (Lasso)IEEE Transactions on Information Theory, 2009
- Shrinkage Tuning Parameter Selection with a Diverging number of ParametersJournal of the Royal Statistical Society Series B: Statistical Methodology, 2008
- Sparse estimation of large covariance matrices via a nested Lasso penaltyThe Annals of Applied Statistics, 2008
- High-dimensional graphs and variable selection with the LassoThe Annals of Statistics, 2006
- Covariance matrix selection and estimation via penalised normal likelihoodBiometrika, 2006
- A well-conditioned estimator for large-dimensional covariance matricesJournal of Multivariate Analysis, 2004
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle PropertiesJournal of the American Statistical Association, 2001
- Adaptive estimation of a quadratic functional by model selectionThe Annals of Statistics, 2000
- Joint mean-covariance models with applications to longitudinal data: unconstrained parameterisationBiometrika, 1999