Robust Generalized Empirical Likelihood for heavy tailed autoregressions with conditionally heteroscedastic errors

JOURNAL OF MULTIVARIATE ANALYSIS

卷:135

Article

Hill, Jonathan B.

关键词: Empirical Likelihood;    Heavy tails;    Autoregression;    Redescending transformation;    Tail trimming;    Robust estimation;   

DOI  :  10.1016/j.jmva.2014.12.008

来源: Elsevier

【 摘 要 】

We present a robust Generalized Empirical Likelihood estimator and confidence region for the parameters of an autoregress ion that may have a heavy tailed heteroscedastic error. The estimator exploits two transformations for heavy tail robustness: a redescending transformation of the error that robustifies against innovation outliers, and weighted least squares instruments that ensure robustness against heavy tailed regressors. Our estimator is consistent for the true parameter and asymptotically normally distributed irrespective of heavy tails. (C) 2014 Elsevier Inc. All rights reserved.

【 授权许可】

Free