Impact of the periodicity and trend on the FD parameter estimation

Research output: Contribution to journalArticle

Abstract

It is well known that one of the features of long-memory processes is that they tend to have what looks like trends and cycles. A consequence of this property is that it is difficult to distinguish a long-memory process from a nonstationary process. In this paper, we study the impact of the periodicity and trend on different methods for estimating the long-memory processes parameter d.

Details

Authors
Organisations
Research areas and keywords

Subject classification (UKÄ) – MANDATORY

  • Probability Theory and Statistics

Keywords

  • discrete wavelet transform, periodicity, trend, long-memory
Original languageEnglish
Pages (from-to)79-87
JournalJournal of Statistical Computation and Simulation
Volume77
Issue number1
Publication statusPublished - 2007
Publication categoryResearch
Peer-reviewedYes