Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/241956 
Year of Publication: 
2021
Series/Report no.: 
cemmap working paper No. CWP20/21
Publisher: 
Centre for Microdata Methods and Practice (cemmap), London
Abstract: 
We develop two new methods for selecting the penalty parameter for the l1 -penalized high-dimensional M-estimator, which we refer to as the analytic and bootstrap-aftercross-validation methods. For both methods, we derive nonasymptotic error bounds for the corresponding l1 -penalized M-estimator and show that the bounds converge to zero under mild conditions, thus providing a theoretical justification for these methods. We demonstrate via simulations that the finite-sample performance of our methods is much better than that of previously available and theoretically justified methods.
Subjects: 
Penalty parameter selection
penalized M-estimation
high-dimensional models
sparsity
cross-validation
bootstrap
Persistent Identifier of the first edition: 
Document Type: 
Working Paper

Files in This Item:
File
Size
930.66 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.