In search of the best methods for multivariate selection analysis

Methods in Ecology and Evolution - Tập 5 Số 10 - Trang 1095-1109 - 2014
Michael B. Morrissey1
1School of Biology, University of St Andrews, Dyers Brae House, St Andrews, KY16 9TH UK

Tóm tắt

SummaryRegression is an important method for characterizing the form of natural selection from individual‐based data. Many kinds of regression analysis exist, but few are regularly employed in studies of natural selection. I provide an overview of some of the main underused types of regression analysis by applying them to test analyses of viability selection for lamb traits in Soay sheep (Ovis aries). This exercise highlights known problems with existing methods, uncovers some new ones and also reveals ways to harness underused methods to get around these problems.I first estimate selection gradients using generalized linear models, combined with recently published methods for obtaining quantitatively interpretable selection gradient estimates from arbitrary regression models of trait–fitness relationships. I then also apply generalized ridge regression, the lasso and projection‐pursuit regression, in each case also deriving selection gradients. I compare inferences of nonlinear selection by diagonalization of theγmatrix and by projection‐pursuit regression.Selection gradient estimates generally correspond across different regression methods. Although there is little evidence for nonlinear selection in the test data sets, very problematic aspects of the behaviour of analysis based on diagonalization of theγare apparent. In addition to better‐known problems, (i) the direction and magnitude of estimated major axes of quadratic selection are biased towards directions of phenotype that have little variance, and (ii) the magnitudes of selection of major axes of variance‐standardizedγare not themselves interpretable in any standardized way.While all regression‐based methods for analysis of selection have useful properties, projection‐pursuit regression seems to stand out. This method can (i) provide both dimensionality reduction, (ii) be the basis for inference of quantitatively interpretable selection gradients and (iii) by characterizing major axes of selection, rather than of linear or quadratic selection separately, provide biologically interpretable inference of nonlinear selection.

Từ khóa


Tài liệu tham khảo

10.1098/rstb.2009.0150

10.1111/j.1420-9101.2006.01164.x

10.1086/587805

10.1890/06-1171.1

Clutton‐Brock T.H., 2004, Soay Sheep Dynamics and Selection in an Island Population

10.2307/5330

10.1086/303274

10.1101/SQB.1955.020.01.020

10.1111/j.1600-0587.2012.07348.x

Endler J.A., 1986, Natural Selection in the Wild

10.1111/evo.12310

10.1111/j.1420-9101.2012.02530.x

10.1080/01621459.1981.10477729

Friedman J., 2008, Regularization paths for generalized linear models via coordinate descent, Journal of Statistical Software, 33, 1

10.1093/biomet/asm030

10.1126/science.1070315

10.1111/j.1558-5646.1996.tb03581.x

10.1111/j.1420-9101.2008.01573.x

10.1111/j.0014-3820.2004.tb01592.x

10.1038/nature12489

10.1111/j.1558-5646.1983.tb00236.x

Lockhart R. Taylor J. Tibshirani R.J.&Tibshirani R.(2013)A significance test for the lasso.Available at:http://arxivorg arXiv:1301.7161v2.

10.1016/j.tree.2011.06.009

10.1046/j.1365-2656.1999.00299.x

10.1111/j.1558-5646.1987.tb02457.x

10.1111/evo.12385

10.1111/j.1558-5646.2011.01444.x

10.1111/evo.12077

Morrissey M., 2014, gsg: Calculation of Selection Coefficients

10.1111/j.1558-5646.2012.01632.x

10.1086/664686

10.1111/j.1558-5646.1989.tb02569.x

10.1098/rspb.2007.1361

10.1111/j.1558-5646.2009.00874.x

10.1111/j.1558-5646.1989.tb04220.x

Robinson M.R., 2006, Live fast, die young: a balance of natural, sexual and antagonistic selection maintains phenotypic polymorphism of weaponry in male and female soay sheep, Evolution, 60, 2168

10.1111/j.1420-9101.2006.01255.x

10.1111/j.1558-5646.1988.tb02507.x

10.1086/285622

10.1111/j.1558-5646.1986.tb00465.x

10.1111/j.1558-5646.2010.01010.x

10.1111/j.1461-0248.2009.01381.x

10.1111/ele.12174

Sober E., 1984, The Nature of Selection

Tibshirani R., 1996, Regression shrinkage and selection via the lasso, Journal of the Royal Statistical Society, Series B, 58, 267, 10.1111/j.2517-6161.1996.tb02080.x

Tikhonov A.N., 1977, Solution of Ill‐Posed Problems

10.1146/annurev.ecolsys.110308.120232

Wilson K., 2004, Soay Sheep: Dynamics and Selection in an Island Population, 113

10.1201/9781420010404

10.1111/j.1467-9868.2005.00503.x

Thông tin
Thông tin xuất bản

Methods in Ecology and Evolution

Tập 5 Số 10

1095-1109

Thông tin tác giả