Regularization and variable selection for infinite variance autoregressive models

Ganggang Xu, Yanbiao Xiang, Suojin Wang, Zhengyan Lin

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

Autoregressive models with infinite variance are of great importance in modeling heavy-tailed time series and have been well studied. In this paper, we propose a penalized method to conduct model selection for autoregressive models with innovations having Pareto-like distributions with index α∈(0, 2). By combining the least absolute deviation loss function and the adaptive lasso penalty, the proposed method is able to consistently identify the true model and at the same time produce efficient estimators with a convergence rate of n -1/α. In addition, our approach provides a unified way to conduct variable selection for autoregressive models with finite or infinite variance. A simulation study and a real data analysis are conducted to illustrate the effectiveness of our method.

Original languageEnglish (US)
Pages (from-to)2545-2553
Number of pages9
JournalJournal of Statistical Planning and Inference
Volume142
Issue number9
DOIs
StatePublished - Sep 2012
Externally publishedYes

Keywords

  • Adaptive lasso
  • Autoregressive model
  • Infinite variance
  • Least absolute deviation

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Regularization and variable selection for infinite variance autoregressive models'. Together they form a unique fingerprint.

Cite this