Robust estimates for GARCH models

By Nora Muler, Victor J. Yohai. 2008

136 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Finance

View Paper: https://www.semanticscholar.org/paper/47fd228c3bff1f4168e5fd2a4a4bd3cd4d1c9e61

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Finance

Citations in the corpus

Volatility estimation for Bitcoin: Replication and robustness (2019, methodology): “The bounded innovation propagation (BIP)-AR(1) proposed by Muler, Peña and Yohai (2009) and the BIP-GARCH(1,1) of Muler and Yohai (2008) is used to obtain robust estimates of µ t and σ 2 t respectively in equations (1) and (3).”
The impacts of outliers on different estimators for GARCH processes: an empirical study (2009, methodology): “The Monte Carlo simulation of Muler and Yohai [2008] reinforces this impression, even though their simulation is carried out with equidistant outliers.”
GARCH Models (2010, unknown): “…estimation methods for GARCH models have not been discussed here, among them Bayesian methods (see Geweke, 1989), the generalized method of moments (see Rich, Raymond and Butler, 1991), variance targeting (see Francq, Horváth and Zakoı̈an, 2009) and robust methods (see Muler and Yohai, 2008).”
Learning from History: Volatility and Financial Crises (2016, methodology): “We opted (1)See for example, Schwert (1989, 1990); Hamilton and Lin (1996); Fornari and Mele (2009); Corradi et al.”
Robust Forecasting of Dynamic Conditional Correlation GARCH Models (2013, methodology): “Muler and Yohai (2008) (MY) show that one can limit the effect of at on the estimation of the parameters of the GARCH model by using a modified GARCH specification downweighing the effect of past jumps (at−1) on time t conditional variance.”
Beta-t-(E)GARCH (2008, methodology): “In the exponential model, u t 1 = I(yt 1 < 0)(ut 1+1) can be included in the equation for Ltpt 1; while I(yt 1 < 0)y 2 t 1= exp( t 1pt 2) is added to the equation for Stpt 1: As a variation we might follow Nelson (1991) and set Stpt 1 = ( + ) S t 1pt 2 + fjyt 1j exp( t 1pt 2=2) E j"t 1j)g + yt 1 exp”