A0190
Title: Asymptotic behavior of the Laplacian quasi-maximum likelihood estimator of affine causal processes
Authors: Jean Marc Bardet - University Paris Pantheon-Sorbonne (France) [presenting]
Abstract: The consistency and asymptotic normality of the Laplacian Quasi-Maximum Likelihood Estimator (QMLE) is proved for a general class of causal time series including ARMA, AR($\infty$), GARCH, ARCH($\infty$), ARMA-GARCH, APARCH, ARMA-APARCH,..., processes. We notably exhibit the advantages (moment order and robustness) of the Laplacian compared to the classical Gaussian QMLE. Numerical simulations confirms the accuracy of the Laplacian estimator.