Polynomial spline approach for variable selection and estimation in varying coefficient models for time series data

Peng Lai; Jie Meng; Heng Lian

doi:10.1016/j.spl.2014.09.008

Polynomial spline approach for variable selection and estimation in varying coefficient models for time series data

Peng Lai, Jie Meng, Heng Lian

Department of Management

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

We propose the penalized estimator with the smoothly clipped absolute deviation (SCAD) penalty for varying coefficient time series models, which in autoregressive models actually performs lag order selection. Theoretical properties are established. Some numerical examples are also presented.

Original language	English
Pages (from-to)	21-27
Number of pages	7
Journal	Statistics and Probability Letters
Volume	96
DOIs	https://doi.org/10.1016/j.spl.2014.09.008
Publication status	Published - Jan 2015

Keywords

autoregressive models
BIC
B-spline basis
SCAD penalty

Access to Document

10.1016/j.spl.2014.09.008

Cite this

@article{000f0b5debdd40c1849f91a4e996d3fa,

title = "Polynomial spline approach for variable selection and estimation in varying coefficient models for time series data",

abstract = "We propose the penalized estimator with the smoothly clipped absolute deviation (SCAD) penalty for varying coefficient time series models, which in autoregressive models actually performs lag order selection. Theoretical properties are established. Some numerical examples are also presented.",

keywords = "autoregressive models, BIC, B-spline basis, SCAD penalty",

author = "Peng Lai and Jie Meng and Heng Lian",

year = "2015",

month = jan,

doi = "10.1016/j.spl.2014.09.008",

language = "English",

volume = "96",

pages = "21--27",

journal = "Statistics and Probability Letters",

issn = "0167-7152",

publisher = "Elsevier",

}

TY - JOUR

T1 - Polynomial spline approach for variable selection and estimation in varying coefficient models for time series data

AU - Lai, Peng

AU - Meng, Jie

AU - Lian, Heng

PY - 2015/1

Y1 - 2015/1

N2 - We propose the penalized estimator with the smoothly clipped absolute deviation (SCAD) penalty for varying coefficient time series models, which in autoregressive models actually performs lag order selection. Theoretical properties are established. Some numerical examples are also presented.

AB - We propose the penalized estimator with the smoothly clipped absolute deviation (SCAD) penalty for varying coefficient time series models, which in autoregressive models actually performs lag order selection. Theoretical properties are established. Some numerical examples are also presented.

KW - autoregressive models

KW - BIC

KW - B-spline basis

KW - SCAD penalty

UR - http://www.scopus.com/inward/record.url?scp=84907612361&partnerID=8YFLogxK

U2 - 10.1016/j.spl.2014.09.008

DO - 10.1016/j.spl.2014.09.008

M3 - Article

SN - 0167-7152

VL - 96

SP - 21

EP - 27

JO - Statistics and Probability Letters

JF - Statistics and Probability Letters

ER -

Polynomial spline approach for variable selection and estimation in varying coefficient models for time series data

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this