Nuisance-parameter-free changepoint detection in non-stationary series

• Michal Pešta ^[1] ; Martin Wendler ^[2]
  1. [1] Charles University in Prague

     Charles University in Prague

     Chequia

     
  2. [2] Institute of Mathematics and Computer Science, University of Greifswald, Walther-Rathenau-Strasse 47, 17489, Greifswald, Germany
• Localización: Test: An Official Journal of the Spanish Society of Statistics and Operations Research, ISSN-e 1863-8260, ISSN 1133-0686, Vol. 29, Nº. 2, 2020, págs. 379-408
• Idioma: inglés
• DOI: 10.1007/s11749-019-00659-1
• Texto completo no disponible (Saber más ...)
• Resumen

  • Many changepoint detection procedures rely on the estimation of nuisance parameters (like long-run variance). If a change has occurred, estimators might be biased and data adaptive rules for the choice of tuning parameters might not work as expected. If the data are not stationary, this becomes more challenging. The aim of this paper is to present two changepoint tests, which involve neither nuisance nor tuning parameters. This is achieved by combing self-normalization and wild bootstrap. We investigate the asymptotic behavior and show the consistency of the bootstrap under the hypothesis as well as under the alternative, assuming mild conditions on the weak dependence of the time series. As a by-product, a changepoint estimator is introduced and its consistency is proved. The results are illustrated through a simulation study. The new completely data-driven tests are applied to real data examples from finance and hydrology.

• Referencias bibliográficas
  • Anderson TW (1958) An introduction to multivariate statistical analysis. Wiley, New York
  • Antoch J, Hušková M, Prášková Z (1997) Effect of dependence on statistics for determination of change. J Stat Plan Inference 60(2):291–310
  • Betken A (2016) Testing for change-points in long-range dependent time series by means of a self-normalized Wilcoxon test. J Time Ser Anal...
  • Betken A, Wendler M (2018) Subsampling for general statistics under long range dependence. Stat Sin 28(3):1199–1224
  • Billingsley P (1968) Convergence of probability measures, 1st edn. Wiley, New York
  • Bradley RC (2005) Basic properties of strong mixing conditions: a survey and some open questions. Probab Surv 2:107–144
  • Cavaliere G (2005) Unit root tests under time-varying variances. Econ Rev 23(3):259–292
  • Csörgő M, Horváth L (1997) Limit theorems in change-point analysis. Wiley, Chichester
  • Dan W, Pengjiang G, Zhiming X (2017) Detection and estimation of structural change in heavy-tailed sequence. Commun Stat Theory Methods 46(2):815–827
  • Dehling H, Fried R, Wendler M (2015) A robust method for shift detection in time series. arXiv:1506.03345
  • Górecki T, Horváth L, Kokoszka P (2018) Change point detection in heteroscedastic time series. Econ Stat 7:63–88
  • Horváth L, Horváth Z, Hušková M (2008) Ratio tests for change point detection. In: Balakrishnan N, Peña EA, Silvapulle MJ (Eds.), Beyond parametrics...
  • Hušková M, Kirch C (2010) A note on studentized confidence intervals for the change-point. Comput Stat 25(2):269–289
  • Hušková M, Kirch C (2012) Bootstrapping sequential change-point tests for linear regression. Metrika 75(5):673–708
  • Ibragimov IA, Linnik YV (1971) Independent and stationary sequences of random variables. Wolters-Noordhoff, The Netherlands
  • Kim J-Y (2000) Detection of change in persistence of a linear time series. J Econ 95(1):97–116
  • Kim TY (1994) Moment bounds for non-stationary dependent sequences. J Appl Probab 31(3):731–742
  • Kirch C (2006) Resampling methods for the change analysis of dependent data. In: Ph.D. thesis, University of Cologne, Germany
  • Kulperger R (1990) On the distribution of the maximum of brownian bridges with application to regression with correlated errors. J Stat Comput...
  • Móricz F (1976) Moment inequalities and the strong laws of large numbers. Zeitschrift für Wahrscheinlichkeitstheorie und Verwandte Gebiete...
  • Perron P (2006) Dealing with structural breaks. In: Hassani H, Mills T, Patterson K (eds) Palgrave handbook of econometrics, volume 1 of econometric...
  • Peštová B, Pešta M (2015) Testing structural changes in panel data with small fixed panel size and bootstrap. Metrika 78(6):665–689
  • Peštová B, Pešta M (2018) Abrupt change in mean using block bootstrap and avoiding variance estimation. Comput Stat 33(1):413–441
  • Rho Y, Shao X (2015) Inference for time series regression models with weakly dependent and heteroscedastic errors. J Bus Econ Stat 33(2):444–457
  • Rosenblatt M (1971) Markov processes: structure and asymptotic behavior. Springer, Berlin
  • Shao X (2010) The dependent wild bootstrap. J Am Stat Assoc 105(489):218–235
  • Shao X (2011) A simple test of changes in mean in the possible presence of long-range dependence. J Time Ser Anal 32(6):598–606
  • Shao X, Zhang X (2010) Testing for change points in time series. J Am Stat Assoc 105(491):1228–1240
  • Sharipov O, Tewes J, Wendler M (2016) Sequential block bootstrap in a hilbert space with application to change point analysis. Can J Stat...
  • Vogel D, Wendler M (2017) Studentized u-quantile processes under dependence with applications to change-point analysis. Bernoulli 23(4B):3114–3144
  • Wenhua C, Hao J (2016) Ratio testing for changes in the long memory indexes. Int Bus Manag 12(3):62–70
  • Wu C-FJ (1986) Jackknife, bootstrap and other resampling methods in regression analysis. Ann Stat 14(4):1261–1295
  • Yokoyama R (1980) Moment bounds for stationary mixing sequences. Zeitschrift für Wahrscheinlichkeitstheorie und Verwandte Gebiete 52(1):45–57
  • Zhang T, Lavitas L (2018) Unsupervised self-normalized change-point testing for time series. J Am Stat Assoc 113(522):637–648
  • Zhao W, Xia Z, Tian Z (2011) Ratio test to detect change in the variance of linear process. Statistics 45(2):189–198