Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/76016
Title: Stable prediction in high-dimensional linear models
Authors: Lin, BQ
Wang, QH
Zhang, J
Pang, Z 
Keywords: Model averaging
Variable selection
Penalized regression
Screening
Issue Date: 2017
Publisher: Springer
Source: Statistics and computing, 2017, v. 27, no. 5, p. 1401-1412 How to cite?
Journal: Statistics and computing 
Abstract: We propose a Random Splitting Model Averaging procedure, RSMA, to achieve stable predictions in high-dimensional linear models. The idea is to use split training data to construct and estimate candidate models and use test data to form a second-level data. The second-level data is used to estimate optimal weights for candidate models by quadratic optimization under non-negative constraints. This procedure has three appealing features: (1) RSMA avoids model overfitting, as a result, gives improved prediction accuracy. (2) By adaptively choosing optimal weights, we obtain more stable predictions via averaging over several candidate models. (3) Based on RSMA, a weighted importance index is proposed to rank the predictors to discriminate relevant predictors from irrelevant ones. Simulation studies and a real data analysis demonstrate that RSMA procedure has excellent predictive performance and the associated weighted importance index could well rank the predictors.
URI: http://hdl.handle.net/10397/76016
ISSN: 0960-3174
EISSN: 1573-1375
DOI: 10.1007/s11222-016-9694-6
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

3
Last Week
0
Last month
Citations as of Nov 12, 2018

WEB OF SCIENCETM
Citations

4
Last Week
0
Last month
Citations as of Nov 19, 2018

Page view(s)

14
Citations as of Nov 18, 2018

Google ScholarTM

Check

Altmetric


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