Interpreting the evolutionary regression: The interplay between observational and biological errors in phylogenetic comparative studies
2012 (English)In: Systematic Biology, ISSN 1063-5157, E-ISSN 1076-836X, Vol. 61, no 3, 413-425 p.Article in journal (Refereed) Published
Regressions of biological variables across species are rarely perfect. Usually, there are residual deviations fromthe estimated model relationship, and such deviations commonly show a pattern of phylogenetic correlations indicatingthat they have biological causes. We discuss the origins and effects of phylogenetically correlated biological variation inregression studies. In particular, we discuss the interplay of biological deviations with deviations due to observationalor measurement errors, which are also important in comparative studies based on estimated species means. We showhow bias in estimated evolutionary regressions can arise from several sources, including phylogenetic inertia and eitherobservational or biological error in the predictor variables. We show how all these biases can be estimated and correctedfor in the presence of phylogenetic correlations.We present general formulas for incorporating measurement error in linearmodels with correlated data. We also show how alternative regression models, such as major axis and reduced major axisregression, which are often recommended when there is error in predictor variables, are strongly biased when there isbiological variation in any part of the model.We argue that such methods should never be used to estimate evolutionary orallometric regression slopes.
Place, publisher, year, edition, pages
2012. Vol. 61, no 3, 413-425 p.
Adaptation; allometry; major-axis regression; measurement error; phylogenetic comparative method; phylogenetic inertia; reduced major-axis regression; structural equation
Probability Theory and Statistics Evolutionary Biology
Research subject Mathematical Statistics; Statistics; Earth Science with specialization in Environmental Analysis; Earth Science with specialization in Environmental Analysis
IdentifiersURN: urn:nbn:se:uu:diva-241888OAI: oai:DiVA.org:uu-241888DiVA: diva2:781843