Independent contrasts and PGLS regression estimators are equivalent

作者: Simon P. Blomberg , James G. Lefevre , Jessie A. Wells , Mary Waterhouse

DOI: 10.1093/SYSBIO/SYR118

关键词:

摘要: We prove that the slope parameter of ordinary least squares regression phylogenetically independent contrasts (PICs) conducted through origin is identical to method generalized (GLSs) under a Brownian motion model evolution. This equivalence has several implications: 1. Understanding structure linear for GLS provides insight into when and why phylogeny important in comparative studies. 2. The limitations PIC analysis are same as model. In particular, phylogenetic covariance applies only response variable explanatory should be regarded fixed. Calculation PICs variables treated mathematical idiosyncrasy algorithm. 3. Since estimator best unbiased (BLUE), estimated using also BLUE. 4. If different branch lengths algorithm, no longer BLUE, so this not recommended. Finally, we discuss whether or how accommodate analyses, particularly relation problem uncertainty. discussion from both frequentist Bayesian perspectives.

参考文章(66)
Roger A. Horn, Charles R. Johnson, Matrix Analysis Cambridge University Press. ,(1985) , 10.1017/CBO9780511810817
Raymond Séroul, Programming for Mathematicians ,(1999)
Mark D. Pagel, Paul H. Harvey, The comparative method in evolutionary biology ,(1991)
Raymond J Carroll, David Ruppert, Leonard A Stefanski, Ciprian M Crainiceanu, Measurement error in nonlinear models: a modern perspective Chapman & Hall/CRC. ,(2006)
David J. Lunn, Andrew Thomas, Nicky Best, David Spiegelhalter, WinBUGS – A Bayesian modelling framework: Concepts, structure, and extensibility Statistics and Computing. ,vol. 10, pp. 325- 337 ,(2000) , 10.1023/A:1008929526011
Liam J. Revell, Phylogenetic signal and linear regression on species data Methods in Ecology and Evolution. ,vol. 1, pp. 319- 329 ,(2010) , 10.1111/J.2041-210X.2010.00044.X
Bradley P. Carlin, Thomas A. Louis, Bayesian Methods for Data Analysis ,(2008)