Vector autoregressions: lag order uncertainty and least absolute deviations

Hanno (Johannes Wilhelmus Nicolaas) Reuvers

Research output: ThesisDoctoral ThesisInternal

558 Downloads (Pure)

Abstract

Vector autoregressive models are often used to model multiple time series at once. They are applied in fields such as climatology, biology and economy. This dissertation studies: 1) the influence of the number of lags included in the model; and 2) a new parameter estimation method. We have concluded there is no preferred method to determine the number of lags. The new estimation method is extremely flexible and more efficient if the data shows extreme values.
Original languageEnglish
Awarding Institution
  • Maastricht University
Supervisors/Advisors
  • Palm, Franz, Supervisor
  • Urbain, Jean-Pierre, Supervisor
  • Smeekes, Stephan, Co-Supervisor
Award date14 May 2018
Place of PublicationMaastricht
Publisher
Print ISBNs9789462959224
DOIs
Publication statusPublished - 2018

Keywords

  • VAR models
  • model uncertainty
  • time series

Cite this