Monte-Carlo and Bayesian techniques in gravitational wave burst data analysis

Document #:

LIGO-P080034-x0

Document type:

P - Publications

Abstract:

Monte-Carlo simulations are used in the gravitational wave burst detection community to demonstrate and compare the properties of different search techniques. We note that every Monte-Carlo simulation has a corresponding optimal search technique according to both the non-Bayesian Neyman-Pearson criterion and the Bayesian approach, and that this optimal search technique is the Bayesian statistic. When practical, we recommend deriving the optimal statistic for a credible Monte-Carlo simulation, rather than testing ad hoc statistics against that simulation.

Files in Document:

• P080034-00.pdf (156.4 kB)

Other Files:

• P080034-P.pdf (394.1 kB)

Topics:

• Document Migration from the old DCC
• Public relations

Authors:

• Antony Searle

Notes and Changes:

Rev P080034-00-Z:
- Full document number: LIGO-P080034-00-Z
- Author(s): Antony Searle
- Document date: 2008-03-25
- Document received date: 2008-03-25
- Document entry date: 2008-03-25

Publication Information:

http://arxiv.org/abs/0804.1161v1