Shrinkage strategy in stratified random sample subject to measurement error

• Published in: Statistics & probability letters Vol. 81; no. 2; pp. 317 - 325
• Main Author: Nkurunziza, Sévérien
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.02.2011; Elsevier
• Series: Statistics & Probability Letters
• Subjects: Distribution theory; Empirical likelihood; Empirical likelihood Measurement errors RMELE Shrinkage methods UMELE; Exact sciences and technology; General topics; Linear inference, regression; Mathematics; Measurement errors; Probability and statistics; Probability theory and stochastic processes; RMELE; Sciences and techniques of general use; Shrinkage methods; Statistics; UMELE; Measurement errors; Empirical likelihood; RMELE; Shrinkage methods; UMELE; Estimation strategy; Monte Carlo method; Probability theory; Shrinkage estimator; Random error; Stratified sample; Statistical method; Simulation; Maximum likelihood; Measurement error; Likelihood function
• ISSN: 0167-7152; 1879-2103
• DOI: 10.1016/j.spl.2010.10.020

The empirical likelihood estimation approach has been used in statistical applications. In this paper, we consider a stratified random sample subject to measurement error and with this framework, we propose a shrinkage estimation strategy that improves the performance of the maximum empirical likelihood estimator (MELE). Further, we generalize some recent findings that demonstrate the superiority of the shrinkage strategy over the MELE. Monte Carlo simulation results corroborate the established theoretical findings.