|
Activity Number:
|
495
- Changepoints: Making an Impact
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Wednesday, July 31, 2019 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Royal Statistical Society
|
|
Abstract #304367
|
Presentation
|
|
Title:
|
Detecting Changes in Mean in the Presence of Autocovariance
|
|
Author(s):
|
Euan McGonigle* and Rebecca Killick and Matthew Nunes
|
|
Companies:
|
Lancaster University and Lancaster University, UK and University of Bath
|
|
Keywords:
|
changepoint detection;
changepoints
|
|
Abstract:
|
There has been much attention in recent years to the problem of detecting changes in mean in a piecewise constant time series. Often, methods assume that the noise can be taken to be I.I.D. Gaussian, which in practice may not be a reasonable assumption. There is comparatively little work studying the problem of changepoint detection in time series with non-trivial autocovariance structure. In this talk, we present a wavelet-based method to detect changes in mean in time series that exhibit autocovariance. We demonstrate its effectiveness on a financial time series example.
|
Authors who are presenting talks have a * after their name.
