High-dimensional, robust, heteroscedastic variable selection with the adaptive LASSO, and applications to random coefficient regression

High-dimensional, robust, heteroscedastic variable selection with the adaptive LASSO, and applications to random coefficient regression

In this thesis, theoretical results for the adaptive LASSO in high-dimensional, sparse linear regression models with potentially heavy-tailed and heteroscedastic errors are developed. In doing so, the empirical pseudo Huber loss is considered as loss function and the main focus is sign-consistency o...

Whakaahuatanga katoa

I tiakina i:
Ngā taipitopito rārangi puna kōrero
Kaituhi matua: Hermann, Philipp
Ētahi atu kaituhi: Holzmann, Hajo (Prof. Dr.) (BetreuerIn (Doktorarbeit))
Hōputu: Dissertation
Reo:Ingarihi
I whakaputaina: Philipps-Universität Marburg 2021
Ngā marau:
sparsity
variable selection
robust regression
Mathematik
high-dimensional regression
linear
sign-consistency
heteroscedasticity
adaptive LASSO
Huber loss
Mathematics
Urunga tuihono:Kuputuhi katoa PDF
Tags: Tāpirihia he Tūtohu
Keine Tags, Fügen Sie den ersten Tag hinzu!
Whakaahuatanga
Whakarāpopototanga:In this thesis, theoretical results for the adaptive LASSO in high-dimensional, sparse linear regression models with potentially heavy-tailed and heteroscedastic errors are developed. In doing so, the empirical pseudo Huber loss is considered as loss function and the main focus is sign-consistency of the resulting estimator. Simulations illustrate the favorable numerical performance of the proposed methodology in comparison to the ordinary adaptive LASSO. Subsequently, those results are applied to the linear random coefficient regression model, more precisely to the means, variances and covariances of the coefficients. Furthermore, sufficient conditions for the identifiability of the first and second moments, as well as asymptotic results for a fixed number of coefficients are given.
Whakaahuatanga ōkiko:140 Seiten
DOI:10.17192/z2021.0248

Ngā tūemi rite