Bootstrap-based ARMA order selection

Modelling the underlying stochastic process is one of the main goals in the study of many dynamic phenomena, such as signal processing, system identification and time series. The issue is often addressed within the framework of ARMA (Autoregressive Moving Average) paradigm, so that the related task of identification of the ‘true’ order is crucial. As it is well known, the effectiveness of such an approach may be seriously compromised by misspecification errors since they may affect model capabilities in capturing dynamic structures of the process. As a result, inference and empirical outcomes may be heavily misleading. Despite the big number of available approaches aimed at determining the order of an ARMA model, the issue is still open. In this paper, we bring the problem in the framework of bootstrap theory in conjunction with the information-based criterion of Akaike (AIC), and a new method for ARMA model selection will be presented. A theoretical justification for the proposed approach as well as an evaluation of its small sample performances, via simulation study, are given.

[1]  R. Shibata.  Selection of the order of an autoregressive model by Akaike's information criterion , 1976 .

[2]  H. Akaike.  Statistical predictor identification , 1970 .

[3]  Francesco Battaglia.  Metodi di previsione statistica , 2007 .

[4]  Piet M. T. Broersen,et al.  Finite sample properties of ARMA order selection , 2004, IEEE Transactions on Instrumentation and Measurement.

[5]  E. Carlstein.  The Use of Subseries Values for Estimating the Variance of a General Statistic from a Stationary Sequence , 1986 .

[6]  B. M. Pötscher.  Effects of Model Selection on Inference , 1991, Econometric Theory.

[7]  M. B. Rajarshi.  Bootstrap in Markov-sequences based on estimates of transition density , 1990 .

[8]  Efstathios Paparoditis,et al.  A MARKOVIAN LOCAL RESAMPLING SCHEME FOR NONPARAMETRIC ESTIMATORS IN TIME SERIES ANALYSIS , 2001, Econometric Theory.

[9]  T. Ozaki.  On the Order Determination of Arima Models , 1977 .

[10]  A. Bose.  Edgeworth correction by bootstrap in autoregressions , 1988 .

[11]  D. Freedman.  On Bootstrapping Two-Stage Least-Squares Estimates in Stationary Linear Models , 1984 .

[12]  J. Franke,et al.  BOOTSTRAPPING STATIONARY AUTOREGRESSIVE MOVING-AVERAGE MODELS , 1992 .

[13]  Wei Pan,et al.  Bootstrapping Likelihood for Model Selection with Small Samples , 1998 .

[14]  S. Datta,et al.  A Note on Bootstrapping M‐Estimators in ARMA Models , 1999 .

[15]  R. Shibata.  Asymptotically Efficient Selection of the Order of the Model for Estimating Parameters of a Linear Process , 1980 .

[16]  Peter J. Bickel,et al.  A new mixing notion and functional central limit theorems for a sieve bootstrap in time series , 1999 .

[17]  Debashis Kushary,et al.  Bootstrap Methods and Their Application , 2000, Technometrics.

[18]  J. Shao.  Bootstrap Model Selection , 1996 .

[19]  Clifford M. Hurvich,et al.  Regression and time series model selection in small samples , 1989 .

[20]  Salih N. Neftci,et al.  Specification of Economic Time Series Models Using Akaike's Criterion , 1982 .

[21]  Jeremy Berkowitz,et al.  Recent developments in bootstrapping time series , 1996 .

[22]  A Bootstrap Approach for Nonlinear Autoregressions Some Preliminary Results , 1992 .

[23]  R. Shibata.  BOOTSTRAP ESTIMATE OF KULLBACK-LEIBLER INFORMATION FOR MODEL SELECTION , 1997 .

[24]  P. Bühlmann.  Sieve bootstrap for time series , 1997 .

[25]  Bootstrap confidence regions computed from autoregressions of arbitrary order , 2000 .

[26]  Regina Y. Liu.  Moving blocks jackknife and bootstrap capture weak dependence , 1992 .

[27]  Karl Rihaczek,et al.  1. WHAT IS DATA MINING? , 2019, Data Mining for the Social Sciences.

[28]  Abdelhak M. Zoubir.  Model selection: a bootstrap approach , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[29]  Robert Tibshirani,et al.  Bootstrap Methods for Standard Errors, Confidence Intervals, and Other Measures of Statistical Accuracy , 1986 .

[30]  H. Akaike.  A new look at the statistical model identification , 1974 .

[31]  D. Politis.  The Impact of Bootstrap Methods on Time Series Analysis , 2003 .

[32]  Chris Chatfield,et al.  Model uncertainty and forecast accuracy , 1996 .

[33]  V. V. Srinivas,et al.  Post-blackening approach for modeling dependent annual streamflows , 2000 .

[34]  David R. Anderson,et al.  Understanding information criteria for selection among capture-recapture or ring recovery models , 1999 .

[35]  Sangit Chatterjee.  Bootstrapping ARMA Models: Some Simulations , 1986, IEEE Transactions on Systems, Man, and Cybernetics.

[36]  Hui Zou,et al.  Combining time series models for forecasting , 2004, International Journal of Forecasting.

[37]  Sergio G. Koreisha,et al.  The identification of ARMA models , 1990 .

[38]  H. R. K. unsch,et al.  Second Order Correctness of the Blockwise Bootstrap for Stationary Observations , 1996 .

[39]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[40]  Peter Hall.  Resampling a coverage pattern , 1985 .

[41]  R. Bhansali,et al.  Some properties of the order of an autoregressive model selected by a generalization of Akaike∘s EPF criterion , 1977 .

[42]  Michael R. Veall,et al.  Bootstrapping the Process of Model Selection: An Econometric Example , 1992 .

[43]  Ian Witten,et al.  Data Mining , 2000 .

[44]  Lutz Kilian,et al.  Accounting for Lag Order Uncertainty in Autoregressions: the Endogenous Lag Order Bootstrap Algorithm , 1998 .

[45]  Ritei Shibata,et al.  Consistency of model selection and parameter estimation , 1986, Journal of Applied Probability.

[46]  K. Burnham,et al.  Model selection: An integral part of inference , 1997 .

[47]  H. Künsch.  The Jackknife and the Bootstrap for General Stationary Observations , 1989 .

[48]  I. Basawa,et al.  Asymptotic bootstrap validity for finite markov chains , 1990 .

[49]  Sergio G. Koreisha,et al.  A Comparison Between Different Order-Determination Criteria for Identification of ARIMA Models , 1995 .

[50]  E. Hannan.  The Estimation of the Order of an ARMA Process , 1980 .

[51]  K. Song,et al.  Bootstrapping cointegrating regressions , 2006 .

[52]  Joseph P. Romano,et al.  The stationary bootstrap , 1994 .

[53]  Michael H. Neumann.  On Robustness of Model-Based Bootstrap Schemes in Nonparametric Time Series Analysis , 2002 .

[54]  Selection of a linear interpolator for time series , 1993 .

[55]  David Hinkley,et al.  Bootstrap Methods: Another Look at the Jackknife , 2008 .

[56]  Hans R. Künsch,et al.  Matched-block bootstrap for dependent data , 1995 .

[57]  G. Kitagawa,et al.  Generalised information criteria in model selection , 1996 .

[58]  Juan Romo,et al.  Introducing model uncertainty in time series bootstrap , 2001 .

[59]  H. Akaike,et al.  Information Theory and an Extension of the Maximum Likelihood Principle , 1973 .

[60]  Dimitris N. Politis,et al.  Computer-intensive methods in statistical analysis , 1998, IEEE Signal Process. Mag..

[61]  B. G. Quinn,et al.  The determination of the order of an autoregression , 1979 .

[62]  Ching-Zong Wei,et al.  Order selection for same-realization predictions in autoregressive processes , 2005, math/0602326.

[63]  H. Akaike.  Fitting autoregressive models for prediction , 1969 .