A property of projection residuals with applications to concave regression

Dietrich W. Kuhlmann and F. T. Wright

Statistics & Probability Letters, 1993, vol. 16, issue 4, 313-319

Abstract: The residuals of the l-2-projection onto a linear subspace, or more generally onto a closed, convex cone, which contains the constant vectors sum to zero, i.e. if y* is the projection of y, then y1 - y1* + tdot + y2 - y2* + ... + yn* = 0. The analogue of this result for least absolute deviations, as well as for other objective functions, is established. The application of these results in establishing the consistency of the l1 and l2 estimates of concave regression functions is discussed.

Keywords: Characterizing; projections; concave; regression; isotonic; regression; lp-estimates; residuals (search for similar items in EconPapers)
Date: 1993
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/0167-7152(93)90136-7
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:stapro:v:16:y:1993:i:4:p:313-319

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/supportfaq.cws_home/regional
https://shop.elsevie ... _01_ooc_1&version=01

Access Statistics for this article

Statistics & Probability Letters is currently edited by Somnath Datta and Hira L. Koul

More articles in Statistics & Probability Letters from Elsevier
Bibliographic data for series maintained by Catherine Liu ().