Annals of Statistics

Normalized least-squares estimation in time-varying ARCH models

Piotr Fryzlewicz, Theofanis Sapatinas, and Suhasini Subba Rao

Full-text: Open access


We investigate the time-varying ARCH (tvARCH) process. It is shown that it can be used to describe the slow decay of the sample autocorrelations of the squared returns often observed in financial time series, which warrants the further study of parameter estimation methods for the model.

Since the parameters are changing over time, a successful estimator needs to perform well for small samples. We propose a kernel normalized-least-squares (kernel-NLS) estimator which has a closed form, and thus outperforms the previously proposed kernel quasi-maximum likelihood (kernel-QML) estimator for small samples. The kernel-NLS estimator is simple, works under mild moment assumptions and avoids some of the parameter space restrictions imposed by the kernel-QML estimator. Theoretical evidence shows that the kernel-NLS estimator has the same rate of convergence as the kernel-QML estimator. Due to the kernel-NLS estimator’s ease of computation, computationally intensive procedures can be used. A prediction-based cross-validation method is proposed for selecting the bandwidth of the kernel-NLS estimator. Also, we use a residual-based bootstrap scheme to bootstrap the tvARCH process. The bootstrap sample is used to obtain pointwise confidence intervals for the kernel-NLS estimator. It is shown that distributions of the estimator using the bootstrap and the “true” tvARCH estimator asymptotically coincide.

We illustrate our estimation method on a variety of currency exchange and stock index data for which we obtain both good fits to the data and accurate forecasts.

Article information

Ann. Statist., Volume 36, Number 2 (2008), 742-786.

First available in Project Euclid: 13 March 2008

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Primary: 62M10: Time series, auto-correlation, regression, etc. [See also 91B84]
Secondary: 62P20: Applications to economics [See also 91Bxx]

Cross-validation (G)ARCH models kernel smoothing least-squares estimation locally stationary models


Fryzlewicz, Piotr; Sapatinas, Theofanis; Subba Rao, Suhasini. Normalized least-squares estimation in time-varying ARCH models. Ann. Statist. 36 (2008), no. 2, 742--786. doi:10.1214/07-AOS510.

Export citation


  • Bera, A. K. and Higgins, M. L. (1993). ARCH models: Properties, estimation and testing. J. Econom. Surv. 7 305–366.
  • Bhattacharya, R. N., Gupta, V. K. and Waymire, E. (1983). The Hurst effect under trend. J. Appl. Probab. 20 649–662.
  • Bickel, P. J. and Freedman, D. A. (1981). Some asymptotic theory for the bootstrap. Ann. Statist. 9 1196–1217.
  • Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. J. Econometrics 31 307–327.
  • Bose, A. and Mukherjee, K. (2003). Estimating the ARCH parameters by solving linear equations. J. Time Ser. Anal. 24 127–136.
  • Dahlhaus, R. (1997). Fitting time series models to nonstationary processes. Ann. Statist. 25 1–37.
  • Dahlhaus, R. and Subba Rao, S. (2006). Statistical inference for time-varying ARCH processes. Ann. Statist. 34 1075–1114.
  • Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation. Econometrica 50 987–1008.
  • Fan, J. and Yao, Q. (2003). Nonlinear Time Series. Springer, New York.
  • Fan, J., Jiang, J., Zhang, C. and Zhou, Z. (2003). Time-dependent diffusion models for term structure dynamics. Statist. Sinica 13 965–992.
  • Franke, J. and Kreiss, J.-P. (1992). Bootstrapping stationary autoregressive moving average models J. Time Ser. Anal. 13 297–317.
  • Fryzlewicz, P., Sapatinas, T. and Subba Rao, S. (2006). A Haar–Fisz technique for locally stationary volatility estimation. Biometrica 93 687–704.
  • Giraitis, L., Kokoszka, P. and Leipus, R. (2000). Stationary ARCH models: Dependence structure and central limit theorem. Econometric Theory 16 3–22.
  • Giraitis, L., Leipus, R. and Surgailis, D. (2005). Recent advances in ARCH modelling. In Long Memory in Economics (A. Kirman and G. Teyssiere, eds.) 3–38. Springer, Berlin.
  • Giraitis, L. and Robinson, P. (2001). Whittle estimation of GARCH models. Econometric Theory 17 608–631.
  • Hall, P. and Heyde, C. (1980). Martingale Limit Theory and its Applications. Academic Press, New York.
  • Hart, J. (1996). Some automated methods for smoothing time-dependent data. J. Nonparametr. Statist. 6 115–142.
  • Horváth, L., Kokoszka, P. and Teyssiére, G. (2001). Empirical process of the squared residuals of an ARCH process. Ann. Statist. 29 445–469.
  • Horváth, L. and Liese, F. (2004). Lp-estimators in ARCH models. J. Statist. Plann. Inference 119 277–309.
  • Ling, S. (2007). Self-weighted and local quasi-maximum likelihood estimators for ARMA-GARCH/IGARCH models. J. Econom. 140 849–873.
  • Mercurio, D. and Spokoiny, V. (2004a). Statistical inference for time-inhomogeneous volatility models. Ann. Statist. 32 577–602.
  • Mercurio, D. and Spokoiny, V. (2004b). Estimation of time dependent volatility via local change point analysis. Preprint.
  • Mikosch, T. and Stărică, C. (2000). Is it really long memory we see in financial returns? In Extremes and Integrated Risk Management (P. Embrechts, ed.) 149–168. Risk Books, London.
  • Mikosch, T. and Stărică, C. (2003). Long-range dependence effects and ARCH modelling. In Theory and Applications of Long Range Dependence (P. Doukhan, G. Oppenheim and M. S. Taqqu, eds.) 439–459. Birkhäuser, Boston.
  • Mikosch, T. and Stărică, C. (2004). Non-stationarities in financial time series, the long-range dependence, and the IGARCH effects. Rev. Econ. Statist. 86 378–390.
  • Paparoditis, E. and Politis, D. N. (2007). Resampling and subsampling for financial time series. In Handbook of Financial Time Series (T. Andersen, R. A. Davis, J.-P. Kreiss and T. Mikosch, eds.). Springer, New York. To appear.
  • Shephard, N. (1996). Statistical aspects of ARCH and stochastic volatility. In Time Series Models in Econometric, Finance and Other Fields (D. R. Cox, D. V. Hinkley and O. E. Barndorff-Nielsen, eds.) 1–67. Chapman and Hall, London.
  • Straumann, D. (2005). Estimation in Conditionally Heteroscedastic Time Series Models. Springer, New York.
  • Stărică, C. (2003). Is GARCH (1, 1) as good a model as the Nobel prize accolades would imply? Preprint.
  • Stărică, C. and Granger, C. W. J. (2005). Non-stationarities in stock returns. Rev. Econ. Statist. 87 503–522.
  • Subba Rao, S. (2006). On some nonstationary, nonlinear random processes and their stationary approximations. Adv. in Appl. Probab. 38 1153–1172.
  • Taylor, S. C. (1986). Modelling Financial Time Series. Wiley, Chichester.