Estimation of long-memory parameters for seasonal fractional ARIMA with stable innovations

M. Ndongo (1) , A. Kâ Diongue (1) , A. Diop (1) , Simplice Dossou-Gbété (2)

1 LERSTAD - laboratoire d'Etudes et de recherches en Statistiques et Développement
2 LMAP - Laboratoire de Mathématiques et de leurs Applications [Pau]

We carry out finite sample size parameter estimation methods for long-memory parameters of the class of seasonal fractional ARIMA with stable innovations. In particular, we consider the semiparametric method studied in Reisen et al. (2006) [27] and two Whittle approaches: the classical Whittle method and a method based on a Markov Chains Monte Carlo (MCMC) procedure. The performance of the methods is discussed using a Monte Carlo simulation. © 2009 Elsevier B.V. All rights reserved.

Domaines: Probabilités [math.PR]

M. Ndongo, A. Kâ Diongue, A. Diop, Simplice Dossou-Gbété. Estimation of long-memory parameters for seasonal fractional ARIMA with stable innovations. Statistical Methodology, 2010, 7 (2), pp.141-151. ⟨10.1016/j.stamet.2009.12.002⟩. ⟨hal-00865074⟩