We introduce a low dimensional function of the site frequency spectrum that
is tailor-made for distinguishing coalescent models with multiple mergers from
Kingman coalescent models with population growth, and use this function to
construct a hypothesis test between these two model classes. The null and
alternative sampling distributions of our statistic are intractable, but its
low dimensionality renders these distributions amenable to Monte Carlo
estimation. We construct kernel density estimates of the sampling distributions
based on simulated data, and show that the resulting hypothesis test
dramatically improves on the statistical power of a current state-of-the-art
method. A key reason for this improvement is the use of multi-locus data, in
particular averaging observed site frequency spectra across unlinked loci to
reduce sampling variance. We also demonstrate the robustness of our method to
nuisance and tuning parameters, and argue that it is readily generalisable for
applications in hypothesis testing, parameter inference and experimental
design.
Description
[1701.07787] Multi-locus data distinguishes between population growth and multiple merger coalescents
%0 Generic
%1 koskela2017multilocus
%A Koskela, Jere
%D 2017
%K lambda_coalescent population_genetics site_frequency_spectrum statistics
%T Multi-locus data distinguishes between population growth and multiple
merger coalescents
%U http://arxiv.org/abs/1701.07787
%X We introduce a low dimensional function of the site frequency spectrum that
is tailor-made for distinguishing coalescent models with multiple mergers from
Kingman coalescent models with population growth, and use this function to
construct a hypothesis test between these two model classes. The null and
alternative sampling distributions of our statistic are intractable, but its
low dimensionality renders these distributions amenable to Monte Carlo
estimation. We construct kernel density estimates of the sampling distributions
based on simulated data, and show that the resulting hypothesis test
dramatically improves on the statistical power of a current state-of-the-art
method. A key reason for this improvement is the use of multi-locus data, in
particular averaging observed site frequency spectra across unlinked loci to
reduce sampling variance. We also demonstrate the robustness of our method to
nuisance and tuning parameters, and argue that it is readily generalisable for
applications in hypothesis testing, parameter inference and experimental
design.
@misc{koskela2017multilocus,
abstract = {We introduce a low dimensional function of the site frequency spectrum that
is tailor-made for distinguishing coalescent models with multiple mergers from
Kingman coalescent models with population growth, and use this function to
construct a hypothesis test between these two model classes. The null and
alternative sampling distributions of our statistic are intractable, but its
low dimensionality renders these distributions amenable to Monte Carlo
estimation. We construct kernel density estimates of the sampling distributions
based on simulated data, and show that the resulting hypothesis test
dramatically improves on the statistical power of a current state-of-the-art
method. A key reason for this improvement is the use of multi-locus data, in
particular averaging observed site frequency spectra across unlinked loci to
reduce sampling variance. We also demonstrate the robustness of our method to
nuisance and tuning parameters, and argue that it is readily generalisable for
applications in hypothesis testing, parameter inference and experimental
design.},
added-at = {2017-02-01T19:32:49.000+0100},
author = {Koskela, Jere},
biburl = {https://www.bibsonomy.org/bibtex/21100d39d6b823aaa090fae0507b81730/peter.ralph},
description = {[1701.07787] Multi-locus data distinguishes between population growth and multiple merger coalescents},
interhash = {b0d982bfeac1853ae1e10a89dd7608cd},
intrahash = {1100d39d6b823aaa090fae0507b81730},
keywords = {lambda_coalescent population_genetics site_frequency_spectrum statistics},
timestamp = {2017-02-01T19:32:49.000+0100},
title = {Multi-locus data distinguishes between population growth and multiple
merger coalescents},
url = {http://arxiv.org/abs/1701.07787},
year = 2017
}