Determination of confidence limits for experiments with low numbers of counts

Ralph P. Kraft; David N. Burrows; John A. Nousek

doi:10.1086/170124

Determination of confidence limits for experiments with low numbers of counts

Ralph P. Kraft, David N. Burrows, John A. Nousek

Astronomy & Astrophysics

Research output: Contribution to journal › Article › peer-review

390 Scopus citations

Abstract

We compare two different methods, classical and Bayesian, for determining confidence intervals involving Poisson-distributed data. We are specifically concerned with cases where the number of counts observed is small and is comparable to the mean number of background counts. We give our reasons for preferring the Bayesian over the classical method. Tables of confidence limits calculated by the Bayesian method are provided for quick reference.

Original language	English (US)
Pages (from-to)	344-355
Number of pages	12
Journal	Astrophysical Journal
Volume	374
Issue number	1
DOIs	https://doi.org/10.1086/170124
State	Published - Jun 10 1991

All Science Journal Classification (ASJC) codes

Astronomy and Astrophysics
Space and Planetary Science

Access to Document

10.1086/170124

Cite this

@article{9247444f6f774aa78e735b2a3e102e07,

title = "Determination of confidence limits for experiments with low numbers of counts",

abstract = "We compare two different methods, classical and Bayesian, for determining confidence intervals involving Poisson-distributed data. We are specifically concerned with cases where the number of counts observed is small and is comparable to the mean number of background counts. We give our reasons for preferring the Bayesian over the classical method. Tables of confidence limits calculated by the Bayesian method are provided for quick reference.",

author = "Kraft, {Ralph P.} and Burrows, {David N.} and Nousek, {John A.}",

year = "1991",

month = jun,

day = "10",

doi = "10.1086/170124",

language = "English (US)",

volume = "374",

pages = "344--355",

journal = "Astrophysical Journal",

issn = "0004-637X",

publisher = "IOP Publishing Ltd.",

number = "1",

}

TY - JOUR

T1 - Determination of confidence limits for experiments with low numbers of counts

AU - Kraft, Ralph P.

AU - Burrows, David N.

AU - Nousek, John A.

PY - 1991/6/10

Y1 - 1991/6/10

N2 - We compare two different methods, classical and Bayesian, for determining confidence intervals involving Poisson-distributed data. We are specifically concerned with cases where the number of counts observed is small and is comparable to the mean number of background counts. We give our reasons for preferring the Bayesian over the classical method. Tables of confidence limits calculated by the Bayesian method are provided for quick reference.

AB - We compare two different methods, classical and Bayesian, for determining confidence intervals involving Poisson-distributed data. We are specifically concerned with cases where the number of counts observed is small and is comparable to the mean number of background counts. We give our reasons for preferring the Bayesian over the classical method. Tables of confidence limits calculated by the Bayesian method are provided for quick reference.

UR - http://www.scopus.com/inward/record.url?scp=0013003073&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0013003073&partnerID=8YFLogxK

U2 - 10.1086/170124

DO - 10.1086/170124

M3 - Article

AN - SCOPUS:0013003073

SN - 0004-637X

VL - 374

SP - 344

EP - 355

JO - Astrophysical Journal

JF - Astrophysical Journal

IS - 1

ER -

Determination of confidence limits for experiments with low numbers of counts

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this