Please use this identifier to cite or link to this item:
Title: Model selection in regression based on pre-smoothing
Authors: AERTS, Marc 
HENS, Niel 
Simonoff, Jeffrey S.
Issue Date: 2010
Source: JOURNAL OF APPLIED STATISTICS, 37 (9). p. 1455-1472
Abstract: In this paper, we investigate the effect of pre-smoothing on model selection. Christobal et al 6 showed the beneficial effect of pre-smoothing on estimating the parameters in a linear regression model. Here, in a regression setting, we show that smoothing the response data prior to model selection by Akaike's information criterion can lead to an improved selection procedure. The bootstrap is used to control the magnitude of the random error structure in the smoothed data. The effect of pre-smoothing on model selection is shown in simulations. The method is illustrated in a variety of settings, including the selection of the best fractional polynomial in a generalized linear model.
Notes: [Aerts, Marc; Hens, Niel] Hasselt Univ, Interuniv Inst Biostat & Stat Bioinformat, B-3590 Diepenbeek, Belgium. [Simonoff, Jeffrey S.] NYU, Leonard N Stern Sch Business, New York, NY 10012 USA.
Keywords: Akaike information criterion; fractional polynomial; latent variable model; model selection; pre-smoothing;Akaike information criterion; fractional polynomial; latent variable model; model selection; pre-smoothing
Document URI:
ISSN: 0266-4763
e-ISSN: 1360-0532
DOI: 10.1080/02664760903046086
ISI #: 000281652200003
Category: A1
Type: Journal Contribution
Validations: ecoom 2011
Appears in Collections:Research publications

Files in This Item:
File Description SizeFormat 
Aerts_et_al_(author_version)[1].pdfarticle355.13 kBAdobe PDFView/Open
Show full item record

Google ScholarTM



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