penalized EM algorithm incorporating missing data mechanism for Gaussian parameter estimation

Missing data rates could depend on the targeted values in many settings, including mass spectrometry‐based proteomic profiling studies. Here, we consider mean and covariance estimation under a multivariate Gaussian distribution with non‐ignorable missingness, including scenarios in which the dimensi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Biometrics Jg. 70; H. 2; S. 312 - 322
Hauptverfasser: Chen, Lin S, Prentice, Ross L, Wang, Pei
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States Blackwell Publishers 01.06.2014
Blackwell Publishing Ltd
International Biometric Society
Schlagworte:
Algorithms
Analytical estimating
BIOMETRIC METHODOLOGY
Biometrics
biometry
Biometry - methods
Computer Simulation
Covariance
Covariance matrices
Data imputation
Estimating techniques
Estimation methods
Expectation-maximization (EM) algorithm
Fungal Proteins - analysis
Humans
Likelihood Functions
Mass Spectrometry
Maximum penalized likelihood estimate
Missing data
Models, Statistical
Multivariate Analysis
Normal Distribution
Not-missing-at-random (NMAR)
Parameter estimation
Proteomics
Proteomics - statistics & numerical data
Sample size
Statistical variance
Not-missing-at-random (NMAR)
Maximum penalized likelihood estimate
Expectation-maximization (EM) algorithm
ISSN:0006-341X, 1541-0420, 1541-0420
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Missing data rates could depend on the targeted values in many settings, including mass spectrometry‐based proteomic profiling studies. Here, we consider mean and covariance estimation under a multivariate Gaussian distribution with non‐ignorable missingness, including scenarios in which the dimension (p) of the response vector is equal to or greater than the number (n) of independent observations. A parameter estimation procedure is developed by maximizing a class of penalized likelihood functions that entails explicit modeling of missing data probabilities. The performance of the resulting “penalized EM algorithm incorporating missing data mechanism (PEMM)” estimation procedure is evaluated in simulation studies and in a proteomic data illustration.
Bibliographie:http://dx.doi.org/10.1111/biom.12149
ArticleID:BIOM12149
ark:/67375/WNG-6GCNFTGB-N
istex:5E4F452A5A48D3AE79C29D81327297D7EEC9FB61
ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0006-341X
1541-0420
1541-0420
DOI:10.1111/biom.12149