Journal article
Reduced rank stochastic regression with a sparse singular value decomposition
Journal of the Royal Statistical Society: Series B (Statistical Methodology), Vol.74(2), pp.203-221
03/2012
DOI: 10.1111/j.1467-9868.2011.01002.x
Abstract
For a reduced rank multivariate stochastic regression model of rank r*, the regression coefficient matrix can be expressed as a sum of r* unit rank matrices each of which is proportional to the outer product of the left and right singular vectors. For improving predictive accuracy and facilitating interpretation, it is often desirable that these left and right singular vectors be sparse or enjoy some smoothness property. We propose a regularized reduced rank regression approach for solving this problem. Computation algorithms and regularization parameter selection methods are developed, and the properties of the new method are explored both theoretically and by simulation. In particular, the regularization method proposed is shown to be selection consistent and asymptotically normal and to enjoy the oracle property. We apply the proposed model to perform biclustering analysis with microarray gene expression data.
Details
- Title: Subtitle
- Reduced rank stochastic regression with a sparse singular value decomposition
- Creators
- Kun ChenKung‐Sik ChanNils Chr Stenseth
- Resource Type
- Journal article
- Publication Details
- Journal of the Royal Statistical Society: Series B (Statistical Methodology), Vol.74(2), pp.203-221
- Publisher
- Blackwell Publishing Ltd; Oxford, UK
- DOI
- 10.1111/j.1467-9868.2011.01002.x
- ISSN
- 1369-7412
- eISSN
- 1467-9868
- Grant note
- DOI: 10.13039/100000001, name: US National Science Foundation, award: NSF-0934617
- Language
- English
- Date published
- 03/2012
- Academic Unit
- Statistics and Actuarial Science; Radiology
- Record Identifier
- 9983985986102771
Metrics
28 Record Views