Home > Research > Publications & Outputs > Bayesian detection of abnormal segments in mult...

Research

Associated organisational units

Electronic data

Links

Text available via DOI:

Keywords

View graph of relations

Bayesian detection of abnormal segments in multiple time series

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Bayesian detection of abnormal segments in multiple time series. / Bardwell, Lawrence; Fearnhead, Paul.
In: Bayesian Analysis, Vol. 12, No. 1, 01.2017, p. 193-218.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Bardwell, L & Fearnhead, P 2017, 'Bayesian detection of abnormal segments in multiple time series', Bayesian Analysis, vol. 12, no. 1, pp. 193-218. https://doi.org/10.1214/16-BA998

APA

Bardwell, L., & Fearnhead, P. (2017). Bayesian detection of abnormal segments in multiple time series. Bayesian Analysis, 12(1), 193-218. https://doi.org/10.1214/16-BA998

Vancouver

Bardwell L, Fearnhead P. Bayesian detection of abnormal segments in multiple time series. Bayesian Analysis. 2017 Jan;12(1):193-218. Epub 2014 Dec 17. doi: 10.1214/16-BA998

Author

Bardwell, Lawrence ; Fearnhead, Paul. / Bayesian detection of abnormal segments in multiple time series. In: Bayesian Analysis. 2017 ; Vol. 12, No. 1. pp. 193-218.

Bibtex

@article{c5dbd2e4f07744c1934c64b68729717d,
title = "Bayesian detection of abnormal segments in multiple time series",
abstract = "We present a novel Bayesian approach to analysing multiple time-series with the aim of detecting abnormal regions. These are regions where the properties of the data change from some normal or baseline behaviour. We allow for the possibility that such changes will only be present in a, potentially small, subset of the time-series. We develop a general model for this problem, and show how it is possible to accurately and efficiently perform Bayesian inference, based upon recursions that enable independent sampling from the posterior distribution. A motivating application for this problem comes from detecting copy number variation (CNVs), using data from multiple individuals. Pooling information across individuals can increase the power of detecting CNVs, but often a specific CNV will only be present in a small subset of the individuals. We evaluate the Bayesian method on both simulated and real CNV data, and give evidence that this approach is more accurate than a recently proposed method for analysing such data.",
keywords = "stat.AP, stat.CO, BARD, Changepoint Detection, Copy Number Variation , PASS",
author = "Lawrence Bardwell and Paul Fearnhead",
year = "2017",
month = jan,
doi = "10.1214/16-BA998",
language = "English",
volume = "12",
pages = "193--218",
journal = "Bayesian Analysis",
issn = "1936-0975",
publisher = "Carnegie Mellon University",
number = "1",

}

RIS

TY - JOUR

T1 - Bayesian detection of abnormal segments in multiple time series

AU - Bardwell, Lawrence

AU - Fearnhead, Paul

PY - 2017/1

Y1 - 2017/1

N2 - We present a novel Bayesian approach to analysing multiple time-series with the aim of detecting abnormal regions. These are regions where the properties of the data change from some normal or baseline behaviour. We allow for the possibility that such changes will only be present in a, potentially small, subset of the time-series. We develop a general model for this problem, and show how it is possible to accurately and efficiently perform Bayesian inference, based upon recursions that enable independent sampling from the posterior distribution. A motivating application for this problem comes from detecting copy number variation (CNVs), using data from multiple individuals. Pooling information across individuals can increase the power of detecting CNVs, but often a specific CNV will only be present in a small subset of the individuals. We evaluate the Bayesian method on both simulated and real CNV data, and give evidence that this approach is more accurate than a recently proposed method for analysing such data.

AB - We present a novel Bayesian approach to analysing multiple time-series with the aim of detecting abnormal regions. These are regions where the properties of the data change from some normal or baseline behaviour. We allow for the possibility that such changes will only be present in a, potentially small, subset of the time-series. We develop a general model for this problem, and show how it is possible to accurately and efficiently perform Bayesian inference, based upon recursions that enable independent sampling from the posterior distribution. A motivating application for this problem comes from detecting copy number variation (CNVs), using data from multiple individuals. Pooling information across individuals can increase the power of detecting CNVs, but often a specific CNV will only be present in a small subset of the individuals. We evaluate the Bayesian method on both simulated and real CNV data, and give evidence that this approach is more accurate than a recently proposed method for analysing such data.

KW - stat.AP

KW - stat.CO

KW - BARD

KW - Changepoint Detection

KW - Copy Number Variation

KW - PASS

U2 - 10.1214/16-BA998

DO - 10.1214/16-BA998

M3 - Journal article

VL - 12

SP - 193

EP - 218

JO - Bayesian Analysis

JF - Bayesian Analysis

SN - 1936-0975

IS - 1

ER -