File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Supervised Sparse and Functional Principal Component Analysis
Title | Supervised Sparse and Functional Principal Component Analysis |
---|---|
Other Titles | Regularization of Principal Component Analysis and Its Applications |
Authors | |
Keywords | Regularized PCA Supervised dimension reduction Penalized likelihood Low rank approximation Latent variable |
Issue Date | 2015 |
Publisher | International Statistical Institute. |
Citation | Proceedings of the 60th World Statistics Congress of the International Statistical Institute (ISI2015), Rio de Janeiro, Brazil, 26-31 July 2015 How to Cite? |
Abstract | Principal component analysis (PCA) is an important tool for dimension reduction in multivariate
analysis. Regularized PCA methods, such as sparse PCA and functional PCA, have been developed to
incorporate special features in many real applications. Sometimes additional variables (referred to as
supervision) are measured on the same set of samples, which can potentially drive low-rank structures
of the primary data of interest. Classical PCA methods cannot make use of such supervision data. In
this paper, we propose a supervised sparse and functional principal component (SupSFPC) framework
that can incorporate supervision information to recover underlying structures that are more
interpretable. The framework unifies and generalizes several existing methods and flexibly adapts to
the practical scenarios at hand. The SupSFPC model is formulated in a hierarchical fashion using
latent variables. We develop an efficient modified expectation-maximization algorithm for parameter
estimation. We also implement fast data-driven procedures for tuning parameter selection. Our
comprehensive simulation and real data examples demonstrate the advantages of SupSFPC. |
Description | IPS005: Recent Advances in Functional Data Analysis |
Persistent Identifier | http://hdl.handle.net/10722/239415 |
ISBN |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Li, G | - |
dc.contributor.author | Shen, H | - |
dc.contributor.author | Huang, JZ | - |
dc.date.accessioned | 2017-03-20T02:27:56Z | - |
dc.date.available | 2017-03-20T02:27:56Z | - |
dc.date.issued | 2015 | - |
dc.identifier.citation | Proceedings of the 60th World Statistics Congress of the International Statistical Institute (ISI2015), Rio de Janeiro, Brazil, 26-31 July 2015 | - |
dc.identifier.isbn | 978-90-73592-35-3 | - |
dc.identifier.uri | http://hdl.handle.net/10722/239415 | - |
dc.description | IPS005: Recent Advances in Functional Data Analysis | - |
dc.description.abstract | Principal component analysis (PCA) is an important tool for dimension reduction in multivariate analysis. Regularized PCA methods, such as sparse PCA and functional PCA, have been developed to incorporate special features in many real applications. Sometimes additional variables (referred to as supervision) are measured on the same set of samples, which can potentially drive low-rank structures of the primary data of interest. Classical PCA methods cannot make use of such supervision data. In this paper, we propose a supervised sparse and functional principal component (SupSFPC) framework that can incorporate supervision information to recover underlying structures that are more interpretable. The framework unifies and generalizes several existing methods and flexibly adapts to the practical scenarios at hand. The SupSFPC model is formulated in a hierarchical fashion using latent variables. We develop an efficient modified expectation-maximization algorithm for parameter estimation. We also implement fast data-driven procedures for tuning parameter selection. Our comprehensive simulation and real data examples demonstrate the advantages of SupSFPC. | - |
dc.language | eng | - |
dc.publisher | International Statistical Institute. | - |
dc.relation.ispartof | World Statistics Congress, 2015 | - |
dc.subject | Regularized PCA | - |
dc.subject | Supervised dimension reduction | - |
dc.subject | Penalized likelihood | - |
dc.subject | Low rank approximation | - |
dc.subject | Latent variable | - |
dc.title | Supervised Sparse and Functional Principal Component Analysis | - |
dc.title.alternative | Regularization of Principal Component Analysis and Its Applications | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Shen, H: haipeng@hku.hk | - |
dc.identifier.authority | Shen, H=rp02082 | - |
dc.identifier.hkuros | 265417 | - |
dc.publisher.place | The Hague, The Netherlands | - |