Cookies?
Library Header Image
LSE Research Online LSE Library Services

Weighted least absolute deviations estimation for ARMA models with infinite variance

Pan, Jiazhu and Wang, Hui and Yao, Qiwei (2007) Weighted least absolute deviations estimation for ARMA models with infinite variance. Econometric Theory, 23 (5). pp. 852-879. ISSN 1469-4360

[img]
Preview
PDF
Download (461kB) | Preview

Identification Number: 10.1017/S0266466607070363

Abstract

For autoregressive moving average (ARMA) models with infinite variance innovations, quasi-likelihood-based estimators (such as Whittle estimators) suffer from complex asymptotic distributions depending on unknown tail indices. This makes statistical inference for such models difficult. In contrast, the least absolute deviations estimators (LADE) are more appealing in dealing with heavy tailed processes. In this paper, we propose a weighted least absolute deviations estimator (WLADE) for ARMA models. We show that the proposed WLADE is asymptotically normal, is unbiased, and has the standard root-n convergence rate even when the variance of innovations is infinity. This paves the way for statistical inference based on asymptotic normality for heavy-tailed ARMA processes. For relatively small samples numerical results illustrate that the WLADE with appropriate weight is more accurate than the Whittle estimator, the quasi-maximum-likelihood estimator (QMLE), and the Gauss–Newton estimator when the innovation variance is infinite and that the efficiency loss due to the use of weights in estimation is not substantial.

Item Type: Article
Official URL: http://journals.cambridge.org/action/displayJourna...
Additional Information: © 2007 Cambridge University Press
Subjects: H Social Sciences > HB Economic Theory
H Social Sciences > HA Statistics
Sets: Departments > Statistics
Collections > Economists Online
Date Deposited: 13 Jun 2008 09:21
Last Modified: 24 Jun 2014 14:03
Projects: 10471005
Funders: Engineering and Physical Sciences Research Council, Natural Science Foundation of China
URI: http://eprints.lse.ac.uk/id/eprint/5405

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics