Kybernetika 48 no. 3, 550-566, 2012

Copula approach to residuals of regime-switching models

Anna Petričková and Magda Komorníková


The autocorrelation function describing the linear dependence is not suitable for description of residual dependence of the regime-switching models. In this contribution, inspired by Rakonczai (\cite{Rak09}), we will model the residual dependence of the regime-switching models (SETAR, LSTAR and ESTAR) with the autocopulas (Archimedean, EV and their convex combinations) and construct improved quality models for the original real time series.


time series, autocopula, residuals, regime-switching models


93E12, 62A10


  1. B. Akintug and P. F. Rasmussen: A Markov switching model for annual hydrologic time series. Water Resour. Res. 41 (2005).   CrossRef
  2. J. Arlt and M. Arltová: Finanční časové rady. Grada Publishing a. s., Praha 2003.   CrossRef
  3. W. A. Brock, W. D. Dechert, J. A. Scheinkman and B. Le Baron: A test for independence based on the correlation dimension. Econometr. Rev. 15 (1996), 197-235.   CrossRef
  4. S. D. Campbell: Specification Testing and Semiparametric Estimation of Regime Switching Models: An Examination of the US Short Term Interest Rate. Department of Economics, Brown University, 2002.   CrossRef
  5. R. Dacco and S. Satchell: Why do regime-switching models forecast so badly? J. Forecast. 18 (1999), 1-16.   CrossRef
  6. P. Embrechts, F. Lindskog and A. McNail: Modeling dependence with copulas and applications to risk management. In: Handbook of Heavy Tailed Distributions in Finance (S. Rachev, ed.), Elsevier 8 (2001), pp. 329-384.   CrossRef
  7. W. Enders and R. Pascalau: Pretesting the Out-of-sample Forecasting Properties of STAR Models. \url{, 2010}.   CrossRef
  8. P. H. Franses and D. Van Dijk: Non-linear Time Series Models in Empirical Finance. Cambridge University Press, Cambridge 2000.   CrossRef
  9. C. Genest and A. C. Favre: Everything you always wanted to know about copula modeling but were afraid to ask. J. Hydrolog. Engrg. (2007), 347-368.   CrossRef
  10. K. Ghoudi, A. Khoudraji and L. P. Rivest: Propriétés statistisques des copules de valeurs extremes bidimensionnelles. Canad. J. Statist. 26 (1998), 1, 187-197.   CrossRef
  11. C. W. J. Granger and T. Teräsvirta: Modelling Nonlinear Economic Relationships. Oxford University Press, Oxford 1993.   CrossRef
  12. S. Grønneberg and N. L. Hjort: The copula information criterion. In: Statistical Research Report 7, Dept. of Math. University of Oslo, 2008.   CrossRef
  13. J. D. Hamilton: A new approach to the economic analysis of nonstationary time series subject to change in regime. Econometrica 57 (1989), 357-384.   CrossRef
  14. H. Joe: Models and Dependence Concepts. Chapman and Hall, London 1997.   CrossRef
  15. J. Komorník and M. Komorníková: Copula approach to residuals of Markov-Switching models for economic time series. In: Proc. AGOP 2011, pp. 39-43.   CrossRef
  16. A. Montgomery, V. Zarnowitz, R. Tsay and G. Tiao: Forecasting the U.S. unemployment rate. J. Amer. Statist. Assoc. 93 (1998), 478-493.   CrossRef
  17. R. B. Nelsen: An introduction to copulas. In: Lecture Notes in Statistics 139, Springer-Verlag, New York 1999.   CrossRef
  18. A. Prokhorov: A goodness-of-fit test for copulas. In: MPRA Paper 9998, 2008, online at \url{}.   CrossRef
  19. P. Rakonczai: On modeling and prediction of multivariate extremes with applications to enviromental data. In: Licentiate Theses in Mathematical Sciences (2009), pp. 83-109.   CrossRef
  20. P. Rakonczai, L. Márkus and A. Zempléni: Autocopulas: Investigating the interdependence structure of stationary time series. Methodology Comput. Appl. Probab. 14 (2012), 1, 149-167.   CrossRef
  21. T. Teräsvirta: Specification, estimation, and evaluation of smooth transition autoregressive models. J. Amer. Statist. Assoc. 89 (1994), 208-218.   CrossRef
  22. T. Teräsvirta: Forecasting economic variables with nonlinear models. In: Handbook of Economic Forecasting (G. Elliot, C. Granger, and A. Timmermann, eds.), Elsevier 8, Amsterdam 2006.   CrossRef
  23. H. White: Maximum likelihood estimation of misspecified models. Econometrica 50 (1982), 1-26.   CrossRef