Time series models with asymmetric innovations |
| |
| Authors: | Moti L. Tiku Wing Keung Wong Guorui Bian |
| |
| Affiliation: | 1. Department of Mathematics and Statistics , McMaster University , Hamilton ON L8S 4KL, Hamilton, Canada;2. Department of Economics Department oi Statistics , National University of Singapore , 119 260, Singapore |
| |
| Abstract: | We consider AR(q) models in time series with asymmetric innovations represented by two families ofdistributions: (i) gamma with support IR : (0, ∞), and (ii) generalized logistic with support IR:(-∞,∞). Since the ML (maximum likelihood) estimators are intractable, we derive the MML (modified maximum likelihood) estimators of the parameters and show that they are remarkably efficient besides being easy to compute. We investigate the efficiency properties of the classical LS (least squares) estimators. Their efficiencies relative to the proposed MML estimators are very low. |
| |
| Keywords: | Time series gamma distribution generalized logistic nonnormality robustness modified likelihood hypothesis testing power function |
|
|
