Use this URL to cite or link to this record in EThOS: http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.635915
Title: Unit root testing in ARMA models : a likelihood ratio approach
Author: Hernandez, Juan R.
ISNI:       0000 0004 5358 1742
Awarding Body: University of Essex
Current Institution: University of Essex
Date of Award: 2014
Availability of Full Text:
Access from EThOS:
Abstract:
In this thesis I propose a Likelihood Ratio test to test for a unit root in ARMA(l, 1) models. In Chapter 1 I present an introduction to the unit root testing literature and motivate the ARMA(l, 1) structure. In Chapter :2 I detail, from the estimation stage, how to obtain the test statistic and provide consistency and limiting distribution results. The Monte Carlo experiments show that for a large enough sample the power functions of the test are close to the Asymptotic Power Envelope. In a power comparison exercise, the Likelihood Ratio test outperforms the Augmented Dickey Fuller test. In Chapter :3 I extend the Likelihood Ratio test to account for deterministic terms and provide the corresponding asymptotic results. The empirical analysis shows that, for a large enough sample and a large enough true Moving A verage, the Likelihood Ratio tests are close to the Asymptotic Power Envelope.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.635915  DOI: Not available
Share: