Prediction intervals and regions for multivariate time series models with sieve bootstrap

• Autorzy: Różański R. , Chłapiński G. , Hławka M. , Jamróz K. , Kawecki M. , Zagdański A.

Identyfikatory

DOI

10.19195/0208-4147.38.2.5

• Języki publikacji: EN

Abstrakty

EN

In the paper, the construction of unconditional bootstrap prediction intervals and regions for some class of second order stationary multivariate linear time series models is considered. Our approach uses the sieje bootstrap procedure introduced by Kreiss (1992) and Bühlmann (1997). Basic theoretical results concerning consistency of the bootstrap replications and the bootstrap prediction regions are proved. We present a simulation study comparing the proposed bootstrap methods with the Box-Jenkins approach.

Słowa kluczowe

EN

multivariate time series models; vector of time series; sieve bootstrap; prediction regions; simultaneous prediction intervals

• Wydawca: Wrocław University of Science and Technology
• Czasopismo: Probability and Mathematical Statistics
• Rocznik: 2018
• Tom: Vol. 38, Fasc. 2
• Strony: 317--357
• Opis fizyczny: Bibliogr. 30 poz., tab.

Twórcy

autor

Różański R.

• Faculty of Pure and Applied Mathematics, Wrocław University of Science and Technology, 27 Wybrzeże Wyspiańskiego, 50-370 Wrocław, Poland

autor

Chłapiński G.

• KRUK S.A., Wrocław

autor

Hławka M.

• Krajowy Rejestr Długów, Biuro Informacji Gospodarczej SA, Wrocław

autor

Jamróz K.

• Santander Bank Polska S.A., Wrocław

autor

Kawecki M.

• IT Consulting Maciej Kawecki, Wrocław

autor

Zagdański A.

• Faculty of Pure and Applied Mathematics, Wrocław University of Science and Technology, 27 Wybrzeże Wyspiańskiego, 50-370 Wrocław, Poland

Bibliografia

• [1] A. M. Alonso, D. Peña, and J. Romo, On sieve bootstrap prediction intervals, Statist. Probab. Lett. 65 (1) (2003), pp. 13-20.
• [2] A. M. Alonso, D. Peña, and J. Romo, Introducing model uncertainty by moving blocks bootstrap, Statist. Papers 47 (2) (2006), pp. 167-179.
• [3] T. W. Anderson, The Statistical Analysis of Time Series, Wiley, New York 1971.
• [4] Yu. K. Belyaev and O. Seleznjev, Approaching in distribution with applications to resampling of stochastic processes, Scand. J. Stat. 27 (2) (2000), pp. 371-384.
• [5] Yu. K. Belyaev and S. Sjöstedt-de Luna, Weakly approaching sequences of random distributions, J. Appl. Probab. 37 (3) (2000), pp. 807-822.
• [6] P. J. Bickel and D. A. Freedman, Some asymptotic theory for the bootstrap, Ann. Statist. 9 (6) (1981), pp. 1196-1217.
• [7] P. J. Brockwell and R. A. Davis, Time Series: Theory and Methods, second edition, Springer, New York 1991.
• [8] P. Bühlmann, Moving-average representation of autoregressive approximations, Stochastic Process. Appl. 60 (2) (1995), pp. 331-342.
• [9] P. Bühlmann, Sieve bootstrap for time series, Bernoulli 3 (2) (1997), pp. 123-148.
• [10] P. Bühlmann, Sieve bootstrap for smoothing in nonstationary time series, Ann. Statist. 26 (1) (1998), pp. 48-83.
• [11] T. Di Battista, S. A. Gattone, and M. Granturco, VAR-models for predicting biodiversity, J. Math. Stat. 1 (4) (2005), pp. 312-315.
• [12] B. Efron and R. J. Tibshirani, An Introduction to the Bootstrap, Chapman and Hall, New York 1993.
• [13] D. Fresoli, E. Ruiz, and L. Pascual, Bootstrap multi-step forecasts of non-Gaussian VAR models, Int. J. Forecast. 31 (2015), pp. 834-848.
• [14] U. Grenander, Abstract Inference,Wiley Ser. Probab. Math. Statist.,Wiley, New York 1981.
• [15] E. J. Hannan and M. Deistler, The Statistical Theory of Linear Systems,Wiley, New York 1988.
• [16] E. J. Hannan and L. Kavalieris, Regression, autoregression models, J. Time Series Anal. 7 (1) (1986), pp. 27-49.
• [17] J. H. Kim, Asymptotic and bootstrap prediction regions for vector autoregression, Int. J. Forecast. 15 (1999), pp. 393-403.
• [18] J.-P. Kreiss, Bootstrap procedures for AR(∞)-processes, in: Bootstrapping and Related Techniques, K. H. Jöckel, G. Rothe, and W. Sendler (Eds.), Springer, New York 1992, pp. 107-113.
• [19] S. N. Lahiri, Resampling Methods for Dependent Data, Springer, New York 2003.
• [20] H. Lütkepohl, New Introduction to Multiple Time Series Analysis, Springer, Berlin 2005.
• [21] M. Meyer and J. Kreiss, On the vector autoregressive sieve bootstrap, J. Time Series Anal. 36 (3) (2015), pp. 377-397.
• [22] S. Mirmirani and H. C. Li, A comparison of VAR and neural networks with genetic algorithm in forecasting price of oil, Adv. Econom. 19 (2004), pp. 203-223.
• [23] D. N. Politis, J. P. Romano, and M. Wolf, Subsampling, Springer, New York 1999.
• [24] R. Różański and A. Zagdański, On the consistency of sieve bootstrap prediction intervals for stationary time series, Discuss. Math. Probab. Stat. 24 (1) (2004), pp. 5-40.
• [25] J. R. Schott, Matrix Analysis for Statistics, third edition, Wiley, Hoboken, NJ, 2017.
• [26] X. Q. Shi, C. J. Wu, and J. H. Chen, Weak and strong representations for quantile processes from finite populations with application to simulation size in resampling inference, Canad. J. Statist. 18 (2) (1990), pp. 141-148.
• [27] R. S. Tsay, Analysis of Financial Time Series, third edition, Wiley, Hoboken, NJ, 2010.
• [28] R. S. Tsay, Multivariate Time Series Analysis: With R and Financial Applications, Wiley, Hoboken, NJ, 2014.
• [29] A. Zagdański, On the construction and properties of bootstrap-t prediction intervals for stationary time series, Probab. Math. Statist. 25 (1) (2005), pp. 133-153.
• [30] A. Zygmund, Trigonometric Series, Vol. I, Cambridge University Press, London-New York 1968.

Uwagi

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).