Comments on: High-dimensional simultaneous inference with the bootstrap
Accepted version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
Lockhart, RA
Samworth, RJ
Abstract
We congratulate the authors on their stimulating contribution to the burgeoning high-dimensional inference literature. The bootstrap offers such an attractive methodology in these settings, but it is well-known that its naive application in the context of shrinkage/superefficiency is fraught with danger (e.g. Samworth, 2003; Chatterjee and Lahiri, 2011). The authors show how these perils can be elegantly sidestepped by working with de-biased, or de-sparsified, versions of estimators.
Description
Keywords
Confidence intervals, De-biased estimator, High-dimensional inference
Journal Title
Test
Conference Name
Journal ISSN
1133-0686
1863-8260
1863-8260
Volume Title
26
Publisher
Sociedad de Estadistica e Investigacion Operativa
Publisher DOI
Sponsorship
Engineering and Physical Sciences Research Council (EP/J017213/1)
Leverhulme Trust (PLP-2014-353)
Leverhulme Trust (PLP-2014-353)
EPSRC (EP/J017213/1), Leverhulme Trust (PLP-2014-353)