Open AccessAsymptotic for Lasso Estimator in High-Dimensional Repeated Measurements Model
Author(s) -
Naser Oda Jassim,
Andul Hussein Saber Al-Mouel
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1818/1/012039
Subject(s) - asymptotic distribution , estimator , consistency (knowledge bases) , mathematics , lasso (programming language) , residual , least squares function approximation , strong consistency , asymptotic analysis , distribution (mathematics) , limiting , statistics , computer science , algorithm , mathematical analysis , discrete mathematics , engineering , world wide web , mechanical engineering
In this paper, we propose high-dimensional repeated measurements model and using the Bridge estimator as penalized method that minimizes the residual sum of squares plus penalty term ∑| θ j | γ . After that, under appropriate conditions, we discuss the consistency and asymptotic behavior of lasso estimator when γ = 1 as especial case and also study the consistency and limiting distribution of the Bridge estimators when γ 1. Moreover, we discuss the asymptotic of estimators by using small parameter and local asymptotic. In other words, we discuss the asymptotic behavior in a triangular array of observations.