Simultaneous sparse model selection and coefficient estimation for heavy-tailed autoregressive processes

DOI10.1080/02331888.2013.848865MaRDI QIDQ5263975zbMATH OpenOpenAlexFDO

Authors Hailin Sang, Yan Sun

Publication date 20 July 2015

Published in Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1112.2682

zbMATH Keywords

strong consistencyheavy tailscausalityautoregressive processoracle propertiespenalized maximum likelihood estimation

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Central limit and other weak theorems (60F05) Stationary stochastic processes (60G10)

Abstract: We propose a sparse coefficient estimation and automated model selection procedure for autoregressive (AR) processes with heavy-tailed innovations based on penalized conditional maximum likelihood. Under mild moment conditions on the innovation processes, the penalized conditional maximum likelihood estimator (PCMLE) satisfies a strong consistency, $O_P(N^{-1/2})$ consistency, and the oracle properties, where N is the sample size. We have the freedom in choosing penalty functions based on the weak conditions on them. Two penalty functions, least absolute shrinkage and selection operator (LASSO) and smoothly clipped average deviation (SCAD), are compared. The proposed method provides a distribution-based penalized inference to AR models, which is especially useful when the other estimation methods fail or under perform for AR processes with heavy-tailed innovations (see cite{Resnick}). A simulation study confirms our theoretical results. At the end, we apply our method to a historical price data of the US Industrial Production Index for consumer goods, and obtain very promising results.

Recommendations

• Regularization and variable selection for infinite variance autoregressive models
• Poisson autoregressive process modeling via the penalized conditional maximum likelihood procedure
• Autoregressive process modeling via the Lasso procedure
• M-estimation for autoregression with infinite variance
• Analysis of autoregressive models with symmetric stable innovations

Cites work

• scientific article; zbMATH DE number 765034 (Why is no real title available?)
• ASYMPTOTIC THEORY FOR A FACTOR GARCH MODEL
• Asymptotically efficient selection of the order of the model for estimating parameters of a linear process
• Autoregressive approximation in nonstandard situations: the fractionally integrated and non-invertible cases
• Autoregressive process modeling via the Lasso procedure
• Covariance matrix estimation for stationary time series
• Econometric analysis of cross section and panel data.
• Estimating the density of the residuals in autoregressive models
• Estimating the dimension of a model
• Estimation of the mean of a multivariate normal distribution
• Fitting autoregressive models for prediction
• Martingale Central Limit Theorems
• Maximum likelihood identification of Gaussian autoregressive moving average models
• Mixing properties of ARMA processes
• New Estimation and Model Selection Procedures for Semiparametric Modeling in Longitudinal Data Analysis
• On some simple, autoregression-based estimation and identification techniques for ARMA models
• On the Non-Negative Garrotte Estimator
• On the measurability and consistency of minimum contrast estimates
• One-step sparse estimates in nonconcave penalized likelihood models
• Order selection for same-realization predictions in autoregressive processes
• Pitfalls of fitting autoregressive models for heavy-tailed time series
• Real Analysis and Probability
• Regularized estimation of large covariance matrices
• Shrinkage estimators of the location parameter for certain spherically symmetric distributions
• Statistical predictor identification
• Stein estimation for non-normal spherically symmetric location families in three dimensions
• TIME SERIES RESIDUALS WITH APPLICATION TO PROBABILITY DENSITY ESTIMATION
• The Adaptive Lasso and Its Oracle Properties
• Time series: theory and methods
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Variable selection for Cox's proportional hazards model and frailty model
• Variable selection using MM algorithms

Cited in

(5)

• Penalized multiply robust estimation in high-order autoregressive processes with missing explanatory variables
• Sparseness, consistency and model selection for Markov regime-switching Gaussian autoregressive models
• Bayesian empirical likelihood inference and order shrinkage for autoregressive models
• Regularization and variable selection for infinite variance autoregressive models
• Poisson autoregressive process modeling via the penalized conditional maximum likelihood procedure

This page was built for publication: Simultaneous sparse model selection and coefficient estimation for heavy-tailed autoregressive processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5263975)