A novel approach for choosing summary statistics in approximate Bayesian computation
Aeschbacher S, Beaumont M, Futschik A. 2012. A novel approach for choosing summary statistics in approximate Bayesian computation. Genetics. 192(3), 1027–1047.
Download (ext.)
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3522150/
[Submitted Version]
Journal Article
| Published
| English
Scopus indexed
Author
Aeschbacher, SimonISTA;
Beaumont, Mark;
Futschik, Andreas
Department
Abstract
The choice of summary statistics is a crucial step in approximate Bayesian computation (ABC). Since statistics are often not sufficient, this choice involves a trade-off between loss of information and reduction of dimensionality. The latter may increase the efficiency of ABC. Here, we propose an approach for choosing summary statistics based on boosting, a technique from the machine learning literature. We consider different types of boosting and compare them to partial least squares regression as an alternative. To mitigate the lack of sufficiency, we also propose an approach for choosing summary statistics locally, in the putative neighborhood of the true parameter value. We study a demographic model motivated by the re-introduction of Alpine ibex (Capra ibex) into the Swiss Alps. The parameters of interest are the mean and standard deviation across microsatellites of the scaled ancestral mutation rate (θanc = 4 Ne u), and the proportion of males obtaining access to matings per breeding season (ω). By simulation, we assess the properties of the posterior distribution obtained with the various methods. According to our criteria, ABC with summary statistics chosen locally via boosting with the L2-loss performs best. Applying that method to the ibex data, we estimate θanc ≈ 1.288, and find that most of the variation across loci of the ancestral mutation rate u is between 7.7×10−4 and 3.5×10−3 per locus per generation. The proportion of males with access to matings is estimated to ω ≈ 0.21, which is in good agreement with recent independent estimates.
Publishing Year
Date Published
2012-11-01
Journal Title
Genetics
Acknowledged SSUs
Volume
192
Issue
3
Page
1027 - 1047
IST-REx-ID
Cite this
Aeschbacher S, Beaumont M, Futschik A. A novel approach for choosing summary statistics in approximate Bayesian computation. Genetics. 2012;192(3):1027-1047. doi:10.1534/genetics.112.143164
Aeschbacher, S., Beaumont, M., & Futschik, A. (2012). A novel approach for choosing summary statistics in approximate Bayesian computation. Genetics. Genetics Society of America. https://doi.org/10.1534/genetics.112.143164
Aeschbacher, Simon, Mark Beaumont, and Andreas Futschik. “A Novel Approach for Choosing Summary Statistics in Approximate Bayesian Computation.” Genetics. Genetics Society of America, 2012. https://doi.org/10.1534/genetics.112.143164.
S. Aeschbacher, M. Beaumont, and A. Futschik, “A novel approach for choosing summary statistics in approximate Bayesian computation,” Genetics, vol. 192, no. 3. Genetics Society of America, pp. 1027–1047, 2012.
Aeschbacher S, Beaumont M, Futschik A. 2012. A novel approach for choosing summary statistics in approximate Bayesian computation. Genetics. 192(3), 1027–1047.
Aeschbacher, Simon, et al. “A Novel Approach for Choosing Summary Statistics in Approximate Bayesian Computation.” Genetics, vol. 192, no. 3, Genetics Society of America, 2012, pp. 1027–47, doi:10.1534/genetics.112.143164.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Link(s) to Main File(s)
Access Level
Open Access
Export
Marked PublicationsOpen Data ISTA Research Explorer
Sources
PMID: 22960215
PubMed | Europe PMC