Transformed Lévy processes as state-dependent wear models

Ji Hwan Cha, Sophie Mercier

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

Abstract

Many wear processes used for modeling accumulative deterioration in a reliability context are nonhomogeneous Lévy processes and, hence, have independent increments, which may not be suitable in an application context. In this work we consider Lévy processes transformed by monotonous functions to overcome this restriction, and provide a new state-dependent wear model. These transformed Lévy processes are first observed to remain tractable Markov processes. Some distributional properties are derived. We investigate the impact of the current state on the future increment level and on the overall accumulated level from a stochastic monotonicity point of view. We also study positive dependence properties and stochastic monotonicity of increments.

Original languageEnglish
Pages (from-to)468-486
Number of pages19
JournalAdvances in Applied Probability
Volume51
Issue number2
DOIs
StatePublished - 1 Jun 2019

Bibliographical note

Publisher Copyright:
© 2019 Applied Probability Trust.

Keywords

  • Reliability
  • deterioration model
  • nonindependent increment
  • positive dependence
  • stochastic order
  • wear process

Fingerprint

Dive into the research topics of 'Transformed Lévy processes as state-dependent wear models'. Together they form a unique fingerprint.

Cite this