Goodness-of-fit tests for Log-GARCH and EGARCH models

Abstract

This paper studies goodness-of-fit tests and specification tests for an extension of the Log-GARCH model, which is both asymmetric and stable by scaling. A Lagrange-multiplier test is derived for testing the extended Log-GARCH against more general formulations taking the form of combinations of Log-GARCH and exponential GARCH (EGARCH). The null assumption of an EGARCH is also tested. Portmanteau goodness-of-fit tests are developed for the extended Log-GARCH. An application to real financial data is proposed.

This is a preview of subscription content, access via your institution.

We’re sorry, something doesn't seem to be working properly.

Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Fig. 1

Notes

  1. 1.

    This effect, typically observed on most stock returns series, means that negative returns have more impact on the volatility than positive returns of the same magnitude.

  2. 2.

    Indeed, as remarked by a referee, a practitioner is essentially faced by three choices: (a) leave returns untransformed, i.e., set \(c = 1\), (b) express returns in terms of percentages, i.e., set \(c = 100\), or (c) express returns in terms of basis points, i.e., set \(c = 10,000\). Clearly, it is desirable that the dynamics of the volatility model be not affected by the choice of c.

References

  1. Berkes I, Horváth L, Kokoszka P (2003) GARCH processes: structure and estimation. Bernoulli 9:201–227

    MathSciNet  Article  MATH  Google Scholar 

  2. Box GEP, Pierce DA (1970) Distribution of the residual autocorrelations in autoregressive-integrated moving average time series models. J Am Stat Assoc 65:1509–1526

    MathSciNet  Article  MATH  Google Scholar 

  3. Carbon M, Francq C (2011) Portmanteau goodness-of-fit test for asymmetric power GARCH models. Austrian J Stat 40:55–64

    Google Scholar 

  4. Escanciano JC (2010) Asymptotic distribution-free diagnostic tests for heteroskedastic time series models. Econom Theor 26:744–773

    MathSciNet  Article  MATH  Google Scholar 

  5. Francq C, Horváth L, Zakoïan JM (2010) Sup-tests for linearity in a general nonlinear AR(1) model. Econom Theor 26:965–993

    MathSciNet  Article  MATH  Google Scholar 

  6. Francq C, Wintenberger O, Zakoïan JM (2013) GARCH models without positivity constraints: exponential or log GARCH? J Econom 177:34–46

    MathSciNet  Article  MATH  Google Scholar 

  7. Francq C, Zakoïan JM (2011) QML estimation of a class of multivariate asymmetric GARCH models. Econom Theor 28:1–28

    MathSciNet  MATH  Google Scholar 

  8. Geweke J (1986) Modeling the persistence of conditional variances: a comment. Econom Rev 5:57–61

    Article  Google Scholar 

  9. Harvey AC, Sucarrat G (2014) EGARCH models with fat tails, skewness and leverage. Comput Stat Data Anal 76:320–338

    MathSciNet  Article  Google Scholar 

  10. Leucht A, Kreiss JP, Neumann M (2015) A model specification test for GARCH(1,1) processes. Scand J Stat 42:1167–1193

    MathSciNet  Article  MATH  Google Scholar 

  11. Li WK (2004) Diagnostic checks in time series. Chapman & Hall, Florida

    Google Scholar 

  12. Li WK, Mak TK (1994) On the squared residual autocorrelations in non-linear time series with conditional heteroscedasticity. J Time Ser Anal 15:627–636

    MathSciNet  Article  MATH  Google Scholar 

  13. Ling S, Li WK (1997) On fractionally integrated autoregressive moving-average time series models with conditional heteroscedasticity. J Am Stat Assoc 92:1184–1194

    MathSciNet  Article  MATH  Google Scholar 

  14. Ljung GM, Box GEP (1978) On the measure of lack of fit in time series models. Biometrika 65:297–303

    Article  MATH  Google Scholar 

  15. Luukkonen R, Saikkonen P, Teräsvirta T (1988) Testing linearity against smooth transition autoregressive models. Biometrika 75:491–499

    MathSciNet  Article  MATH  Google Scholar 

  16. McLeod AI (1978) On the distribution of residual autocorrelations in Box–Jenkins method. J R Stat Soc B 40:296–302

    MATH  Google Scholar 

  17. Milhøj A (1987) A multiplicative parameterization of ARCH models. University of Copenhagen, Department of Statistics, Mimeo

    Google Scholar 

  18. Nelson DB (1991) Conditional heteroskedasticity in asset returns : a new approach. Econometrica 59:347–370

    MathSciNet  Article  MATH  Google Scholar 

  19. Pantula SG (1986) Modeling the persistence of conditional variances: a comment. Econom Rev 5:71–74

    Article  Google Scholar 

  20. Sucarrat G, Grønneberg S, Escribano A (2016) Estimation and inference in univariate and multivariate log-GARCH-X models when the conditional density is unknown. Comput Stat Data Anal 100:582–594

    MathSciNet  Article  Google Scholar 

  21. Wintenberger O (2013) Continuous invertibility and stable QML estimation of the EGARCH(1,1) model. Scand J Stat 40:846–867

    MathSciNet  Article  MATH  Google Scholar 

Download references

Acknowledgments

The authors would like to thank the referees for their helpful comments. Christian Francq and Jean-Michel Zakoïan also gratefully acknowledge financial support from the Ecodec Labex.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Christian Francq.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 210 KB)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Francq, C., Wintenberger, O. & Zakoïan, JM. Goodness-of-fit tests for Log-GARCH and EGARCH models. TEST 27, 27–51 (2018). https://doi.org/10.1007/s11749-016-0506-2

Download citation

Keywords

  • EGARCH
  • LM tests
  • Invertibility of time series models
  • Log-GARCH
  • Portmanteau tests
  • Quasi-maximum likelihood

Mathematics Subject Classification

  • 62M10
  • 62P20