Reply to Robert et al.: Model criticism informs model choice and model comparison
File(s)0912.3182v1.pdf (1.03 MB)
Accepted version
Author(s)
Ratmann, O
Andrieu, C
Wiuf, C
Richardson, S
Type
Journal Article
Abstract
In their letter to PNAS and a comprehensive set of notes on arXiv
[arXiv:0909.5673v2], Christian Robert, Kerrie Mengersen and Carla Chen (RMC)
represent our approach to model criticism in situations when the likelihood
cannot be computed as a way to "contrast several models with each other". In
addition, RMC argue that model assessment with Approximate Bayesian Computation
under model uncertainty (ABCmu) is unduly challenging and question its Bayesian
foundations. We disagree, and clarify that ABCmu is a probabilistically sound
and powerful too for criticizing a model against aspects of the observed data,
and discuss further the utility of ABCmu.
[arXiv:0909.5673v2], Christian Robert, Kerrie Mengersen and Carla Chen (RMC)
represent our approach to model criticism in situations when the likelihood
cannot be computed as a way to "contrast several models with each other". In
addition, RMC argue that model assessment with Approximate Bayesian Computation
under model uncertainty (ABCmu) is unduly challenging and question its Bayesian
foundations. We disagree, and clarify that ABCmu is a probabilistically sound
and powerful too for criticizing a model against aspects of the observed data,
and discuss further the utility of ABCmu.
Date Issued
2010-01-19
Date Acceptance
2010-01-01
Citation
Proceedings of the National Academy of Sciences of the United States of America, 2010, 107 (3), pp.E6-E7
ISSN
0027-8424
Publisher
National Academy of Sciences
Start Page
E6
End Page
E7
Journal / Book Title
Proceedings of the National Academy of Sciences of the United States of America
Volume
107
Issue
3
Is Replaced By
Copyright Statement
© the authors
Identifier
http://arxiv.org/abs/0912.3182v1
Subjects
stat.ME
stat.ME
Notes
Reply to [arXiv:0909.5673v2]
Publication Status
Published
Date Publish Online
2010-01-14