The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Wild bootstrap Ljung-Box test for autocorrelation in vector autoregressive and error correction models

벡터자기회귀모형과 오차수정모형의 자기상관성을 위한 와일드 붓스트랩 Ljung-Box 검정

  • Lee, Myeongwoo (Department of Statistics, Hankuk University of Foreign Studies) ;
  • Lee, Taewook (Department of Statistics, Hankuk University of Foreign Studies)
  • 이명우 (한국외국어대학교 통계학과) ;
  • 이태욱 (한국외국어대학교 통계학과)
  • Received : 2015.12.02
  • Accepted : 2015.12.23
  • Published : 2016.02.29
Download PDF
⟨ Previous Next ⟩

Abstract

We consider the wild bootstrap Ljung-Box (LB) test for autocorrelation in residuals of fitted multivariate time series models. The asymptotic chi-square distribution under the IID assumption is traditionally used for the LB test; however, size distortion tends to occur in the usage of the LB test, due to the conditional heteroskedasticity of financial time series. In order to overcome such defects, we propose the wild bootstrap LB test for autocorrelation in residuals of fitted vector autoregressive and error correction models. The simulation study and real data analysis are conducted for finite sample performance.

본 논문에서는 다변량 시계열 모형 진단을 위해 잔차의 자기상관성 유무를 확인하기 위한 와일드 붓스트랩(wild bootstrap) Ljung-Box(LB) 검정통계량을 연구하였다. 일반적으로 LB 검정은 오차가 서로 독립이며 동일한 분포를 따른다는 IID 가정 하에 유도되는 점근적 카이제곱 분포를 이용한다. 한편 금융시계열 자료는 분산에 조건부 이분산성이 존재하기 때문에 오차의 IID 가정을 만족시키지 못하며 이에 따라 점근적 분포를 이용한 LB 검정은 제1종의 오류를 만족시키지 못하게 된다. 이를 극복하기 위해 와일드 붓스트랩을 이용한 LB 검정법을 제안하고 그 성질을 연구하고자 한다. 벡터자기회귀 모형과 벡터오차수정 모형 등의 다양한 다변량 시계열 모형을 이용하여 모의실험을 실시하는 한편, 코스피 200지수와 지수선물 자료를 이용한 실증분석을 통해 와일드 붓스트랩을 이용한 LB 검정법이 조건부 이분산성의 부정적인 영향을 효과적으로 제거할 수 있음을 입증하였다.

Keywords

References

  1. Ahlgren, N. and Catani, P. (2012). Wild bootstrap tests for autocorrelation in vector autoregressive models, Working Papers 562, Available from: https://helda.helsinki.fi/bitstream/handle/10138/36634/562_978-952-232-178-7.pdf?sequence=1
  2. Bruggemann, R., Lutkepohl, H., and Saikkonen, P. (2006). Residual autocorrelation testing for vector error correction models, Journal of Econometrics, 134, 579-604. https://doi.org/10.1016/j.jeconom.2005.07.006
  3. Catani, P., Terasvirta, T., and Yin, M. (2014). A lagrange multiplier test for testing the adequacy of the constant conditional correlation GARCH Model. CREATES Research Paper 2014-3, Available from: ftp://ftp.econ.au.dk/creates/rp/14/rp14_03.pdf
  4. Davidson, R. and Flachaire, E. (2008). The wild bootstrap, Journal of Econometrics, 146, 162-169. https://doi.org/10.1016/j.jeconom.2008.08.003
  5. Goncalves, S. and Kilian, L. (2004). Bootstrap autoregressions with conditional heteroskedasticity of unknown form, Journal of Econometrics, 123, 89-120. https://doi.org/10.1016/j.jeconom.2003.10.030
  6. Hosking, J. R. M. (1980). The multivariate portmanteau statistic, Journal of the American Statistical Association, 75, 602-608. https://doi.org/10.1080/01621459.1980.10477520
  7. Kwon, D. and Lee, T. (2014). Hedging effectiveness of KOSPI200 index futures through VECM-CC-GARCH model, Journal of the Korean Data Information Science Society, 25, 1449-1466. https://doi.org/10.7465/jkdi.2014.25.6.1449
  8. Li, W. K. and McLeod, A. I. (1981). Distribution of the residual autocorrelation in multivariate ARMA time series models, Journal of the Royal Statistical Society, Series B, 43, 231-239.
  9. Liu, R. (1988). Bootstrap procedures under some non-i.i.d. models, Annals of Statistics, 16, 1696-1708. https://doi.org/10.1214/aos/1176351062
  10. Ljung, G. M. and Box, G. E. P. (1978). On a measure of lack of fit in time series models, Biometrika, 65, 297-303. https://doi.org/10.1093/biomet/65.2.297
  11. Mammen, E. (1993). Bootstrap and wild bootstrap for high dimensional linear models, Annals of Statistics, 21, 255-285. https://doi.org/10.1214/aos/1176349025
  12. Tsay, R. S. (2010). Analysis of Financial Time Series, 2nd ed, John Wiley & Sons, New Jersey.
  13. Tsay, R. S. (2014). Multivariate Time Series with R and Financial Applications, John Wiley & Sons, New Jersey.