File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1111/rssb.12279
- Scopus: eid_2-s2.0-85055455509
- WOS: WOS:000448897700003
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: An imputation-regularized optimization algorithm for high dimensional missing data problems and beyond
Title | An imputation-regularized optimization algorithm for high dimensional missing data problems and beyond |
---|---|
Authors | |
Keywords | Expectation–maximization algorithm Gaussian graphical model Gibbs sampler Imputation consistency Random‐coefficient model |
Issue Date | 2018 |
Publisher | Wiley-Blackwell Publishing Ltd. The Journal's web site is located at http://www.blackwellpublishing.com/journals/RSSB |
Citation | Journal of the Royal Statistical Society. Series B: Statistical Methodology, 2018, v. 80 n. 5, p. 899-926 How to Cite? |
Abstract | Missing data are frequently encountered in high-dimensional problems, but they are usually difficult to deal with using standard algorithms, such as the expectation-maximization (EM) algorithm and its variants. To tackle this difficulty, some problem-specific algorithms have been developed in the literature, but there still lacks a general algorithm. This work is to fill the gap: we propose a general algorithm for high-dimensional missing data problems. The proposed algorithm works by iterating between an imputation step and a consistency step. At the imputation step, the missing data are imputed conditional on the observed data and the current estimate of parameters; and at the consistency step, a consistent estimate is found for the minimizer of a Kullback-Leibler divergence defined on the pseudo-complete data. For high dimensional problems, the consistent estimate can be found under sparsity constraints. The consistency of the averaged estimate for the true parameter can be established under quite general conditions. The proposed algorithm is illustrated using high-dimensional Gaussian graphical models, high-dimensional variable selection, and a random coefficient model. |
Persistent Identifier | http://hdl.handle.net/10722/272098 |
ISSN | 2023 Impact Factor: 3.1 2023 SCImago Journal Rankings: 4.330 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Luo, Y | - |
dc.contributor.author | Liang, FAMING | - |
dc.contributor.author | Jia, BOCHAO | - |
dc.contributor.author | Xue, JINGNAN | - |
dc.contributor.author | Li, QIZAI | - |
dc.date.accessioned | 2019-07-20T10:35:38Z | - |
dc.date.available | 2019-07-20T10:35:38Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | Journal of the Royal Statistical Society. Series B: Statistical Methodology, 2018, v. 80 n. 5, p. 899-926 | - |
dc.identifier.issn | 1369-7412 | - |
dc.identifier.uri | http://hdl.handle.net/10722/272098 | - |
dc.description.abstract | Missing data are frequently encountered in high-dimensional problems, but they are usually difficult to deal with using standard algorithms, such as the expectation-maximization (EM) algorithm and its variants. To tackle this difficulty, some problem-specific algorithms have been developed in the literature, but there still lacks a general algorithm. This work is to fill the gap: we propose a general algorithm for high-dimensional missing data problems. The proposed algorithm works by iterating between an imputation step and a consistency step. At the imputation step, the missing data are imputed conditional on the observed data and the current estimate of parameters; and at the consistency step, a consistent estimate is found for the minimizer of a Kullback-Leibler divergence defined on the pseudo-complete data. For high dimensional problems, the consistent estimate can be found under sparsity constraints. The consistency of the averaged estimate for the true parameter can be established under quite general conditions. The proposed algorithm is illustrated using high-dimensional Gaussian graphical models, high-dimensional variable selection, and a random coefficient model. | - |
dc.language | eng | - |
dc.publisher | Wiley-Blackwell Publishing Ltd. The Journal's web site is located at http://www.blackwellpublishing.com/journals/RSSB | - |
dc.relation.ispartof | Journal of the Royal Statistical Society. Series B: Statistical Methodology | - |
dc.rights | Preprint This is the pre-peer reviewed version of the following article: [Journal of the Royal Statistical Society. Series B: Statistical Methodology, 2018, v. 80 n. 5, p. 899-926], which has been published in final form at [http://dx.doi.org/10.1111/rssb.12279]. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Use of Self-Archived Versions. | - |
dc.subject | Expectation–maximization algorithm | - |
dc.subject | Gaussian graphical model | - |
dc.subject | Gibbs sampler | - |
dc.subject | Imputation consistency | - |
dc.subject | Random‐coefficient model | - |
dc.title | An imputation-regularized optimization algorithm for high dimensional missing data problems and beyond | - |
dc.type | Article | - |
dc.identifier.email | Luo, Y: kurtluo@hku.hk | - |
dc.identifier.authority | Luo, Y=rp02428 | - |
dc.description.nature | preprint | - |
dc.identifier.doi | 10.1111/rssb.12279 | - |
dc.identifier.scopus | eid_2-s2.0-85055455509 | - |
dc.identifier.hkuros | 299561 | - |
dc.identifier.volume | 80 | - |
dc.identifier.issue | 5 | - |
dc.identifier.spage | 899 | - |
dc.identifier.epage | 926 | - |
dc.identifier.isi | WOS:000448897700003 | - |
dc.publisher.place | United Kingdom | - |
dc.identifier.issnl | 1369-7412 | - |