TY - JOUR
T1 - The power of Bayesian evidence in astronomy
AU - Jenkins, C. R.
AU - Peacock, J. A.
PY - 2011/6/1
Y1 - 2011/6/1
N2 - We discuss the use of the Bayesian evidence ratio, or Bayes factor, for
model selection in astronomy. We treat the evidence ratio as a statistic
and investigate its distribution over an ensemble of experiments,
considering both simple analytical examples and some more realistic
cases, which require numerical simulation. We find that the evidence
ratio is a noisy statistic, and thus it may not be sensible to decide to
accept or reject a model based solely on whether the evidence ratio
reaches some threshold value. The odds suggested by the evidence ratio
bear no obvious relationship to the power or Type I error rate of a test
based on the evidence ratio. The general performance of such tests is
strongly affected by the signal-to-noise ratio in the data, the assumed
priors and the threshold in the evidence ratio that is taken as
'decisive'. The comprehensiveness of the model suite under consideration
is also very important. The usefulness of the evidence ratio approach in
a given problem can be assessed in advance of the experiment, using
simple models and numerical approximations. In many cases, this approach
can be as informative as a much more costly full-scale Bayesian analysis
of a complex problem.
AB - We discuss the use of the Bayesian evidence ratio, or Bayes factor, for
model selection in astronomy. We treat the evidence ratio as a statistic
and investigate its distribution over an ensemble of experiments,
considering both simple analytical examples and some more realistic
cases, which require numerical simulation. We find that the evidence
ratio is a noisy statistic, and thus it may not be sensible to decide to
accept or reject a model based solely on whether the evidence ratio
reaches some threshold value. The odds suggested by the evidence ratio
bear no obvious relationship to the power or Type I error rate of a test
based on the evidence ratio. The general performance of such tests is
strongly affected by the signal-to-noise ratio in the data, the assumed
priors and the threshold in the evidence ratio that is taken as
'decisive'. The comprehensiveness of the model suite under consideration
is also very important. The usefulness of the evidence ratio approach in
a given problem can be assessed in advance of the experiment, using
simple models and numerical approximations. In many cases, this approach
can be as informative as a much more costly full-scale Bayesian analysis
of a complex problem.
UR - http://www.scopus.com/inward/record.url?scp=79956215007&partnerID=8YFLogxK
U2 - 10.1111/j.1365-2966.2011.18361.x
DO - 10.1111/j.1365-2966.2011.18361.x
M3 - Article
VL - 413
SP - 2895
EP - 2905
JO - Monthly Notices of the Royal Astronomical Society
JF - Monthly Notices of the Royal Astronomical Society
SN - 0035-8711
ER -