Improved Maximum Likelihood Estimation of ARMA Models

DOI10.1134/S1995080222120101MaRDI QIDQ6389271arXivFDO

Authors Leonardo Di Gangi, Matteo Lapucci, Fabio Schoen, Alessio Sortino

Publication date 26 January 2022

Published in arXiv

Full work available at URL https://doi.org/10.1134/S1995080222120101

Mathematics Subject Classification ID

Nonparametric inference (62Gxx) Artificial intelligence (68Txx)

arXiv classification

math.OCstat.CO

Abstract: In this paper we propose a new optimization model for maximum likelihood estimation of causal and invertible ARMA models. Through a set of numerical experiments we show how our proposed model outperforms, both in terms of quality of the fitted model as well as in the computational time, the classical estimation procedure based on Jones reparametrization. We also propose a regularization term in the model and we show how this addition improves the out of sample quality of the fitted model. This improvement is achieved thanks to an increased penalty on models close to the non causality or non invertibility boundary.

This page was built for publication: Improved Maximum Likelihood Estimation of ARMA Models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6389271)