Computational Statistics

, Volume 20, Issue 4, pp 559–573 | Cite as

SETAR model selection-A bootstrap approach

  • John Öhrvik
  • Gabriella Schoier


The aim of this paper is to propose new selection criteria for the orders of selfexciting threshold autoregressive (SETAR) models. These criteria use bootstrap methodology; they are based on a weighted mean of the apparent error rate in the sample and the average error rate obtained from bootstrap samples not containing the point being predicted. These new criteria are compared with the traditional ones based on the Akaike information criterion (AIC). A simulation study and an example on a real data set end the paper.


Akaike information criterion AR-sieve bootstrap bootstrap model selection criteria moving block bootstrap self-exciting threshold autoregressive models unbiased Akaike information criterion 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Box, G. E. P. and Jenkins, G. M. (1969),Time series Analysisforecasting and control, Holden day.Google Scholar
  2. Buehlmann, P. (1997), Sieve Bootstrap for Time Series,Bernoulli,3, 123–148.MATHCrossRefMathSciNetGoogle Scholar
  3. Carlstein, E., Do, K.-A., Hall, P., Hesterberg, T. and Kuensch, H. R. (1998), Matched-block Bootstrap for Dependent Data,Bernoulli,4, 305–328.MATHCrossRefMathSciNetGoogle Scholar
  4. Chan, K. S., Petruccelli I D., Tong H. and Woolford S. W. (1985), A Multiple Threshold AR(1) Model,Journal of Applied Probability,22, 267–279.MATHCrossRefMathSciNetGoogle Scholar
  5. Chan, K. S. (1993), Consistency and limiting distribution of the least squares estimator of a threshold autoregressive model,Annals of Statistics,21, 520–533.MATHMathSciNetGoogle Scholar
  6. Cheng, B. and Tong, H. (1992), On Consistent Nonparametric Order Determination and Chaos,Journal of Royal Statistical Society,B 54, 427–449.MathSciNetGoogle Scholar
  7. De Gooijer, J. G. (2001), Cross-validation Criteria for SETAR Model Selection,Journal of Time Series Analysis,22, 267–281.MATHCrossRefMathSciNetGoogle Scholar
  8. Efron, B. and Tibshirani, R. J. (1993),An Introduction to the Bootstrap, Chapman & Hall.Google Scholar
  9. Hall, P., Horowitz, J. L. and Jing, B.-Y. (1995), On Blocking Rules for the Block Bootstrap and Dependent Data,Biometrika,82, 561–574.MATHCrossRefMathSciNetGoogle Scholar
  10. Hjorth, J. S. U. (1994),Computer Intensive statistical Methods-Validation, model selection and bootstrap, Chapman & Hall.Google Scholar
  11. Kuensch, H. R. (1989), The Jackknife and the Bootstrap for General Stationary Observations,The Annals of Statistics,17, 1217–1241.MATHMathSciNetGoogle Scholar
  12. Marsaglia, G. (1984), A Current View of Random Number Generators,The Proceedings of the 16th Symposium on the Interface, Atlanta, Elsevier Press.Google Scholar
  13. Moran, P. A. P. (1953), The statistical analysis of the Canadian lynx cycle, I:structure and prediction.Australian Journal of Zoology,1, 163–173.CrossRefGoogle Scholar
  14. Petruccelli, J. D. and Woolford, S.W. (1984), A threshold AR(1) model,Journal of Applied Probability,21, 270–286.MATHCrossRefMathSciNetGoogle Scholar
  15. Shao, J. (1996), Bootstrap Model Selection,Journal of American Statistical Association,91, 655–665.MATHCrossRefGoogle Scholar
  16. Schoier, G. (1999), Strong consistency of a multiple regime threshold AR(1) model,Journal of Italian Statistical Society,8, 75–82.CrossRefGoogle Scholar
  17. Tong, H. and Lim, K. S. (1980), Threshold Autoregression, Limit Cycles and Cyclical Data,Journal of Royal Statistical Society,B 42, 245–292.Google Scholar
  18. Tong, H. (1983),Threshold Models in Non-Linear Time Series Analysis, Lecture Notes in Statistics, Springer-Verlag.Google Scholar
  19. Tong, H. (1990),Non-Linear Time: A dynamical System Approach, Oxford University Press.Google Scholar
  20. Tsay, R. S. (1989), Testing and Modeling Threshold Autoregressive Processes,Journal of American Statistical Association,84, 231–240.MATHCrossRefMathSciNetGoogle Scholar
  21. Wong, C. S. and Li, W. K. (1998), A Note on the Corrected Akaike Information Criterion for Threshold Autoregressive Models,Journal of Time Series Analysis,19, 113–124.MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Physica-Verlag 2005

Authors and Affiliations

  • John Öhrvik
    • 1
  • Gabriella Schoier
    • 2
  1. 1.Department of Medical Epidemiology and BiostatisticsKarolinska InstituteStockholmSweden
  2. 2.Dipartimento di Scienze Economiche e StatisticheUniversitá di TriesteTriesteItaly

Personalised recommendations