Finite-Sample Bias of the Conditional Gaussian Maximum Likelihood Estimator in ARMA Models
ISBN: 978-1-78560-787-5, eISBN: 978-1-78560-786-8
Publication date: 23 June 2016
Abstract
I derive the finite-sample bias of the conditional Gaussian maximum likelihood estimator in ARMA models when the error follows some unknown non-normal distribution. The general procedure relies on writing down the score function and its higher order derivative matrices in terms of quadratic forms in the non-normal error vector with the help of matrix calculus. Evaluation of the bias can then be straightforwardly conducted. I give further simplified bias results for some special cases and compare with the existing results in the literature. Simulations are provided to confirm my simplified bias results.
Keywords
Acknowledgements
Acknowledgements
I am grateful to two anonymous referees and Gloria González-Rivera for their constructive feedback. I also thank the participants in the Advances in Econometrics conference (Riverside, CA) for their valuable comments. I am indebted to Aman Ullah for inspiring me to start this line of research.
Citation
Bao, Y. (2016), "Finite-Sample Bias of the Conditional Gaussian Maximum Likelihood Estimator in ARMA Models", Essays in Honor of Aman Ullah (Advances in Econometrics, Vol. 36), Emerald Group Publishing Limited, Leeds, pp. 207-244. https://doi.org/10.1108/S0731-905320160000036015
Publisher
:Emerald Group Publishing Limited
Copyright © 2016 Emerald Group Publishing Limited