Some Consistency Results for Bayesian Analysis of Long Memory Processes

Abstract: Long memory processes, characterized by slow decay of autocorrelations, have gained substantial attention in various fields, including economics, finance, and signal processing. Bayesian analysis has become a prominent framework for modelling these processes due to its flexibility and the ability to incorporate prior information. This presentation explores the critical topic of consistency in Bayesian analysis of long memory processes. We delve into the fundamental concepts of long memory, highlighting the challenges that arise when applying Bayesian methods to such data. In this talk, we review the key methodologies used to obtain parameter estimates in the presence of long memory. We examine the challenges and some Bayesian solution to this problem. By addressing the consistency of Bayesian analysis in the context of long memory processes, this presentation aims to provide a deeper understanding of the challenges and solutions in modelling and forecasting long-range-dependent data.

Mathematics

Audience: researchers in the topic

OneSchool Seminar

Series comments: This seminar series aims to facilitate sharing and learning about the research of our fellow staff members. Early and mid-career researchers will present a broader context of their work which should be accessible and relatable to the entire School community. Seminars will be held in-person, followed by a friendly gathering and refreshments in the SMRI common room or out on the terrace (weather permitting). Everyone is warmly invited.