Fitting Penalized Estimator for Sparse Covariance Matrix with Left-Censored Data by the EM Algorithm

Estimating the sparse covariance matrix can effectively identify important features and patterns, and traditional estimation methods require complete data vectors on all subjects. When data are left-censored due to detection limits, common strategies such as excluding censored individuals or replaci...

Full description

Saved in:
Bibliographic Details
Main Authors: Shanyi Lin, Qian-Zhen Zheng, Laixu Shang, Ping-Feng Xu, Man-Lai Tang
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/3/423
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850199900166291456
author Shanyi Lin
Qian-Zhen Zheng
Laixu Shang
Ping-Feng Xu
Man-Lai Tang
author_facet Shanyi Lin
Qian-Zhen Zheng
Laixu Shang
Ping-Feng Xu
Man-Lai Tang
author_sort Shanyi Lin
collection DOAJ
description Estimating the sparse covariance matrix can effectively identify important features and patterns, and traditional estimation methods require complete data vectors on all subjects. When data are left-censored due to detection limits, common strategies such as excluding censored individuals or replacing censored values with suitable constants may result in large biases. In this paper, we propose two penalized log-likelihood estimators, incorporating the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>L</mi><mn>1</mn></msub></semantics></math></inline-formula> penalty and SCAD penalty, for estimating the sparse covariance matrix of a multivariate normal distribution in the presence of left-censored data. However, the fitting of these penalized estimators poses challenges due to the observed log-likelihood involving high-dimensional integration over the censored variables. To address this issue, we treat censored data as a special case of incomplete data and employ the Expectation Maximization algorithm combined with the coordinate descent algorithm to efficiently fit the two penalized estimators. Through simulation studies, we demonstrate that both penalized estimators achieve greater estimation accuracy compared to methods that replace censored values with constants. Moreover, the SCAD penalized estimator generally outperforms the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>L</mi><mn>1</mn></msub></semantics></math></inline-formula> penalized estimator. Our method is used to analyze the proteomic datasets.
format Article
id doaj-art-5d68acad9edf40dab0a5cbc1a3b1bf6c
institution OA Journals
issn 2227-7390
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-5d68acad9edf40dab0a5cbc1a3b1bf6c2025-08-20T02:12:30ZengMDPI AGMathematics2227-73902025-01-0113342310.3390/math13030423Fitting Penalized Estimator for Sparse Covariance Matrix with Left-Censored Data by the EM AlgorithmShanyi Lin0Qian-Zhen Zheng1Laixu Shang2Ping-Feng Xu3Man-Lai Tang4School of Mathematics and Statistics, Changchun University of Technology, Changchun 130012, ChinaCollege of Education, Zhejiang Normal University, Jinhua 321004, ChinaCollege of Education, Zhejiang Normal University, Jinhua 321004, ChinaAcademy for Advanced Interdisciplinary Studies & Key Laboratory of Applied Statistics of MOE, Northeast Normal University, Changchun 130024, ChinaDepartment of Physics, Astronomy and Mathematics, School of Physics, Engineering & Computer Science, University of Hertfordshire, Hertfordshire AL10 9AB, UKEstimating the sparse covariance matrix can effectively identify important features and patterns, and traditional estimation methods require complete data vectors on all subjects. When data are left-censored due to detection limits, common strategies such as excluding censored individuals or replacing censored values with suitable constants may result in large biases. In this paper, we propose two penalized log-likelihood estimators, incorporating the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>L</mi><mn>1</mn></msub></semantics></math></inline-formula> penalty and SCAD penalty, for estimating the sparse covariance matrix of a multivariate normal distribution in the presence of left-censored data. However, the fitting of these penalized estimators poses challenges due to the observed log-likelihood involving high-dimensional integration over the censored variables. To address this issue, we treat censored data as a special case of incomplete data and employ the Expectation Maximization algorithm combined with the coordinate descent algorithm to efficiently fit the two penalized estimators. Through simulation studies, we demonstrate that both penalized estimators achieve greater estimation accuracy compared to methods that replace censored values with constants. Moreover, the SCAD penalized estimator generally outperforms the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>L</mi><mn>1</mn></msub></semantics></math></inline-formula> penalized estimator. Our method is used to analyze the proteomic datasets.https://www.mdpi.com/2227-7390/13/3/423sparse covariance matrixExpectation Maximization algorithmpenalized estimatorleft-censored data
spellingShingle Shanyi Lin
Qian-Zhen Zheng
Laixu Shang
Ping-Feng Xu
Man-Lai Tang
Fitting Penalized Estimator for Sparse Covariance Matrix with Left-Censored Data by the EM Algorithm
Mathematics
sparse covariance matrix
Expectation Maximization algorithm
penalized estimator
left-censored data
title Fitting Penalized Estimator for Sparse Covariance Matrix with Left-Censored Data by the EM Algorithm
title_full Fitting Penalized Estimator for Sparse Covariance Matrix with Left-Censored Data by the EM Algorithm
title_fullStr Fitting Penalized Estimator for Sparse Covariance Matrix with Left-Censored Data by the EM Algorithm
title_full_unstemmed Fitting Penalized Estimator for Sparse Covariance Matrix with Left-Censored Data by the EM Algorithm
title_short Fitting Penalized Estimator for Sparse Covariance Matrix with Left-Censored Data by the EM Algorithm
title_sort fitting penalized estimator for sparse covariance matrix with left censored data by the em algorithm
topic sparse covariance matrix
Expectation Maximization algorithm
penalized estimator
left-censored data
url https://www.mdpi.com/2227-7390/13/3/423
work_keys_str_mv AT shanyilin fittingpenalizedestimatorforsparsecovariancematrixwithleftcensoreddatabytheemalgorithm
AT qianzhenzheng fittingpenalizedestimatorforsparsecovariancematrixwithleftcensoreddatabytheemalgorithm
AT laixushang fittingpenalizedestimatorforsparsecovariancematrixwithleftcensoreddatabytheemalgorithm
AT pingfengxu fittingpenalizedestimatorforsparsecovariancematrixwithleftcensoreddatabytheemalgorithm
AT manlaitang fittingpenalizedestimatorforsparsecovariancematrixwithleftcensoreddatabytheemalgorithm