Outlier detection in GARCH models
作者： J.A. Doornik , M. Ooms
DOI:
关键词: Computation 、 Statistics 、 Autoregressive conditional heteroskedasticity 、 Economics 、 Studentized residual 、 Outlier 、 Anomaly detection 、 Null distribution 、 Volatility (finance) 、 Econometrics 、 Generalized extreme value distribution
摘要: We present a new procedure for detecting multiple additive outliers in GARCH(1,1) models at unknown dates. The outlier candidates are the observations with largest standardized residual. First, likelihood-ratio based test determines presence and timing of an outlier. Next, second type (volatility or level). tests shown to be similar respect GARCH parameters. Their null distribution can easily approximated from extreme value distribution, so that computation "p"-values does not require simulation. outperforms alternative methods, especially when it comes determining date apply method returns Dow Jones index, using monthly, weekly, daily data. is extended applied Student-"t" distributed errors.
参考文章(12)
Chung Chen, Lon-Mu Liu, Joint Estimation of Model Parameters and Outlier Effects in Time Series Journal of the American Statistical Association. ,vol. 88, pp. 284- 297 ,(1993) , 10.1080/01621459.1993.10594321
Tim Bollerslev, A CONDITIONALLY HETEROSKEDASTIC TIME SERIES MODEL FOR SPECULATIVE PRICES AND RATES OF RETURN The Review of Economics and Statistics. ,vol. 62, pp. 542- 547 ,(1987) , 10.2307/1925546
Gabriele Fiorentini, Giorgio Calzolari, Lorenzo Panattoni, Analytic derivatives and the computation of GARCH estimates Journal of Applied Econometrics. ,vol. 11, pp. 399- 417 ,(1996) , 10.1002/(SICI)1099-1255(199607)11:4<399::AID-JAE401>3.0.CO;2-R
Shinichi Sakata, Halbert White, HIGH BREAKDOWN POINT CONDITIONAL DISPERSION ESTIMATION WITH APPLICATION TO S&P 500 DAILY RETURNS VOLATILITY Econometrica. ,vol. 66, pp. 529- 567 ,(1998) , 10.2307/2998574
Bovas Abraham, Nihal Yatawara, A SCORE TEST FOR DETECTION OF TIME SERIES OUTLIERS Journal of Time Series Analysis. ,vol. 9, pp. 109- 119 ,(1988) , 10.1111/J.1467-9892.1988.TB00458.X
M. R. Leadbetter, Holger Rootzén, Georg Lindgren, Extremes and Related Properties of Random Sequences and Processes ,(2011)
Neil Shephard, Statistical aspects of ARCH and stochastic volatility Springer US. pp. 1- 67 ,(1996) , 10.1007/978-1-4899-2879-5_1
Ruey S. Tsay, Analysis of Financial Time Series ,(2001)
Jurgen A. Doornik, Multimodality in the GARCH Regression Model Research Papers in Economics. ,(2003)
Christian Gourieroux, ARCH Models and Financial Applications ,(1997)