A robust closed-form estimator for the GARCH(1,1) model

Abstract

In this paper we extend the closed-form estimator for the GARCH(1,1) proposed by Kristensen and Linton (2006) to deal with additive outliers. It has the advantage that is per se more robust that the maximum likelihood estimator (ML) often used to estimate this model, it is easy to implement and does not require the use of any numerical optimization procedure. The robustification of the closed-form estimator is done by replacing the sample autocorrelations by a robust estimator of these correlations and by estimating the volatility using robust filters. The performance of our proposal in estimating the parameters and the volatility of the GARCH(1,1) model is compared with the proposals existing in the literature via intensive Monte Carlo experiments and the results of these experiments show that our proposal outperforms the ML and quasi-maximum likelihood (QMLE) estimators based procedures. Finally, we fit the robust closed-form estimator and the benchmarks to one series of financial returns and analyze their performances in estimating and forecasting the volatility and the Value-at-Risk.JEL-Classifications: C22; C53; C58

Detection of Outliers in the Volatility of Malaysia Shariah Compliant Index Return: The Impulse Indicator Saturation Approach

“…The restriction 0 <̂1 +̂1 ≤ 1 and ̂0 > 0 are always imposed in the estimation procedure. The chosen parameter is similar with the study done by Bahamonde & Veiga (2016) and Carnero et al (2012). Using the benchmark model, In contrast, n is the total number of outliers and T is the total observations.…”

Robust Two-Step Wavelet-Based Inference for Time Series Models

“…Robust estimators of moments, such as autocovariances, include Ma and Genton (2000), Lévy-Leduc et al (2011), andChang andPolitis (2016) (see also Rousseeuw and Croux 1993), and for a review, see, for example, Dürre, Fried, and Liboschik (2015). They have been used by for example, Molinares, Reisen, and Cribari-Neto (2009) as plugin estimators for ARFIMA models (see also Reisen and Molinares 2012), by Sarnaglia, Reisen, and Lévy-Leduc (2010a) for the parameters of the periodic AR model with the Yule-Walker equation and by Bahamonde and Veiga (2016) for the GARCH (1,1). The idea of making the Kalman filter robust was originated with Masreliez and Martin (1977) and Cipra (1992) who proposed robust modifications of exponential smoothing (see also Cipra andHanzak 2011 andMahieu 2010 for a multivariate version).…”

Robust Two-Step Wavelet-Based Inference for Time Series Models

“…They have been used by e.g. Molinares et al (2009) as plugin estimators for ARFIMA models (see also Reisen and Molinares, 2012), by for the parameters of the periodic AR model with the Yule-Walker equation and by Bahamonde and Veiga (2016) for the GARCH(1,1). The idea of making the Kalman filter robust was originated with Masreliez and Martin (1977) and Cipra (1992) who propose robust modifications of exponential smoothing (see also Cipra andHanzak, 2011 and for a multivariate version).…”