Abstract
Multimodel inference refers to the task of making a generalization from several statistical models that correspond to different biological hypotheses and that vary in the degree of how well they fit the data at hand. Several approaches have been developed for such purpose, and these are widely used, mostly for intraspecific data, i.e., in a non-phylogenetic framework, to draw inference from models that consider different predictor variables in different combinations. Adding the phylogenetic component, in theory, calls for a more extended exploitation of these techniques as several hypotheses about the phylogenetic history of species and about the mode of evolution should also be considered, all of which can be flexibly incorporated and combined with different statistical models. Here, we highlight some biological problems that inherently imply multimodel approaches and show how these problems can be tackled in the phylogenetic generalized least squares (PGLS) modeling framework based on information-theoretic approaches (e.g., by using Akaike’s information criterion, AIC) or maximum likelihood. We present a conceptual framework of model selection for phylogenetic comparative analyses, where the goal is to generalize across models that involve different combinations of predictors, phylogenetic hypotheses, parameters describing the mode of evolution, and error structures. Although this overview suggests that a model selection strategy may be useful in several situations, we note that the performance of the approach in the phylogenetic context awaits further evaluation in simulation studies.
The original version of this chapter was revised: Online Practical Material website has been updated. The erratum to this chapter is available at https://doi.org/10.1007/978-3-662-43550-2_23
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
When drawing inference in an IT framework, it is essential to not mix it up with the NHST framework. Most crucially, it does not make sense to select the best model based on AIC and then test its significance or the significance of the predictors it includes.
- 2.
Another way of dealing with model selection uncertainty is to consider the best model confidence set, which contains the models that can be considered as best with some certainty. Different criteria do exist to identify the best model confidence set among which the most popular are to include those models that differ in AIC from the best model by at most some threshold (e.g., 2 or 10) or, alternatively, to include those models for which their summed cumulative Akaike weights (from largest to smallest) just exceed 0.95. In this chapter, we do not consider such subjective thresholds further, and throughout the remaining discussion we refer to model averaging in a sense that it is made across the full model set.
- 3.
It may not be necessarily applied to the current biological example, because allometric regressions are intensively studied (e.g., Bennett and Harvey 1985; Hutcheon et al. 2002; Iwaniuk et al. 2004; Garamszegi et al. 2002). Therefore, results from a large number of studies on other vertebrate taxa may be used to define a narrower and more informative prior. However, in this example simulated on the general situation when no preceding information on the expected relationship is available. Note that technically BayesTraits only allows uniform priors for continuous data.
- 4.
As long as the number of parameters is equal, AIC and ML reveal the same.
References
Alfaro ME, Huelsenbeck JP (2006) Comparative performance of Bayesian and AIC-based measures of phylogenetic model uncertainty. Syst Biol 55(1):89–96. doi:10.1080/10635150500433565
Alfaro ME, Santini F, Brock C, Alamillo H, Dornburg A, Rabosky DL, Carnevale G, Harmon LJ (2009) Nine exceptional radiations plus high turnover explain species diversity in jawed vertebrates. Proc Natl Acad Sci. doi:10.1073/pnas.0811087106
Arima S, Tardella L (2012) Improved harmonic mean estimator for phylogenetic model evidence. J Comput Biol 19(4):418–438. doi:10.1089/cmb.2010.0139
Arnold C, Matthews LJ, Nunn CL (2010) The 10kTrees website: a new online resource for primate hylogeny. Evol Anthropol 19:114–118
Bennett PM, Harvey PH (1985) Brain size, development and metabolism in birds and mammals. J Zool 207:491–509
Blomberg S, Garland TJ, Ives AR (2003) Testing for phylogenetic signal in comparative data: behavioral traits are more laible. Evolution 57:717–745
Bolker B (2007) Ecological models and data in R. Princeton University Press, Princeton and Oxford
Burnham KP, Anderson DR (2002) Model selection and multimodel inference: a practical information-theoretic approach. Springer, New York
Burnham KP, Anderson DR, Huyvaert KP (2011) AIC model selection and multimodel inference in behavioral ecology: some background, observations, and comparisons. Behav Ecol Sociobiol 65(1):23–35
Butler MA, King AA (2004) Phylogenetic comparative analysis: a modeling approach for adaptive evolution. Am Nat 164(6):683–695. doi:10.1086/426002
Chamberlin TC (1890) The method of multiple working hypotheses. Science 15:92–96
Cheverud JM, Dow MM, Leutenegger W (1985) The quantitative assessment of phylogenetic constraints in comparative analyses: sexual dimorphism of body weight among primates. Evolution 39:1335–1351
Claeskens C, Hjort NL (2008) Model selection and model averaging. Cambridge University Press, Cambridge
Cohen J (1994) The earth is round (p < .05). Am Psychol 49(12):997–1003
Collar DC, O’Meara BC, Wainwright PC, Near TJ (2009) Piscivory limits diversification of feeding morphology in centrarchid fishes. Evolution 63:1557–1573
Collar DC, Schulte JA, Losos JB (2011) Evolution of extreme body size disparity in monitor lizards (Varanus). Evolution 65(9):2664–2680. doi:10.1111/j.1558-5646.2011.01335.x
Congdon P (2003) Applied bayesian modelling. Wiley, Chichester
Congdon P (2006) Bayesian statistical modelling, 2nd edn. Wiley, Chichester
de Villemereuil P, Wells JA, Edwards RD, Blomberg SP (2012) Bayesian models for comparative analysis integrating phylogenetic uncertainty. BMC Evol Biol 12. doi:10.1186/1471-2148-12-102
Depraz A, Cordellier M, Hausser J, Pfenninger M (2008) Postglacial recolonization at a snail’s pace (Trochulus villosus): confronting competing refugia hypotheses using model selection. Mol Ecol 17(10):2449–2462. doi:10.1111/j.1365-294X.2008.03760.x
Eklof A, Helmus MR, Moore M, Allesina S (2012) Relevance of evolutionary history for food web structure. Proc Roy Soc B-Biol Sci 279(1733):1588–1596. doi:10.1098/rspb.2011.2149
Felsenstein J (1985) Phylogenies and the comparative method. Am Nat 125:1–15
Freckleton RP, Harvey PH, Pagel M (2002) Phylogenetic analysis and comparative data: a test and review of evidence. Am Nat 160:712–726
Gamerman D, Lopes HF (2006) Markov chain Monte Carlo: stochastic simulation for Bayesian inference. CRC Press, Boca Raton, FL
Garamszegi LZ (2011) Information-theoretic approaches to statistical analysis in behavioural ecology: an introduction. Behav Ecol Sociobiol 65:1–11. doi:10.1007/s00265-010-1028-7
Garamszegi LZ, Møller AP (2007) Prevalence of avian influenza and host ecology. Proc R Soc B 274:2003–2012
Garamszegi LZ, Møller AP (2012) Untested assumptions about within-species sample size and missing data in interspecific studies. Behav Ecol Sociobiol 66:1363–1373
Garamszegi LZ, Møller AP, Erritzøe J (2002) Coevolving avian eye size and brain size in relation to prey capture and nocturnality. Proc R Soc B 269:961–967
Goldberg EE, Igic B (2008) On phylogenetic tests of irreversible evolution. Evolution 62(11):2727–2741. doi:10.1111/j.1558-5646.2008.00505.x
Hadfield JD, Nakagawa S (2010) General quantitative genetic methods for comparative biology: phylogenies, taxonomies and multi-trait models for continuous and categorical characters. J Evol Biol 23:494–508
Hansen TF (1997) Stabilizing selection and the comparative analysis of adaptation. Evolution 51:1341–1351
Hansen TF, Bartoszek K (2012) Interpreting the evolutionary regression: the interplay between observational and biological errors in phylogenetic comparative studies. Syst Biol 61:413–425
Harmon LJ, Losos JB, Jonathan Davies T, Gillespie RG, Gittleman JL, Bryan Jennings W, Kozak KH, McPeek MA, Moreno-Roark F, Near TJ, Purvis A, Ricklefs RE, Schluter D, Schulte Ii JA, Seehausen O, Sidlauskas BL, Torres-Carvajal O, Weir JT, Mooers AØ (2010) Early bursts of body size and shape evolution are rare in comparative data. Evolution 64(8):2385–2396. doi:10.1111/j.1558-5646.2010.01025.x
Hegyi G, Garamszegi LZ (2011) Using information theory as a substitute for stepwise regression in ecology and behavior. Behav Ecol Sociobiol 65:69–76. doi:10.1007/s00265-010-1036-7
Hunt G (2006) Fitting and comparing models of phyletic evolution: random walks and beyond. Paleobiology 32(4):578–601. doi:10.1666/05070.1
Hutcheon JM, Kirsch JW, Garland TJ (2002) A comparative analysis of brain size in relation to foraging ecology and phylogeny in the chiroptera. Brain Behav Evol 60:165–180
Ingram T, Mahler DL (2013) SURFACE: detecting convergent evolution from comparative data by fitting Ornstein-Uhlenbeck models with stepwise Akaike information criterion. Methods Ecol Evol 4(5):416–425. doi:10.1111/2041-210x.12034
Ives AR, Midford PE, Garland T (2007) Within-species variation and measurement error in phylogenetic comparative methods. Syst Biol 56(2):252–270
Iwaniuk AN, Dean KM, Nelson JE (2004) Interspecific allometry of the brain and brain regions in parrots (Psittaciformes): comparisons with other birds and primates. Brain Behav Evol 30:40–59
Jhwueng D-C (2013) Assessing the goodness of fit of phylogenetic comparative methods: a meta-analysis and simulation study. PLoS ONE 8(6):e67001. doi:10.1371/journal.pone.0067001
Johnson JB, Omland KS (2004) Model selection in ecology and evolution. Trends Ecol Evol 19(2):101–108
Konishi S, Kitagawa G (2008) Information criteria and statistical modeling. Springer, New York
Kutsukake N, Innan H (2013) Simulation-based likelihood approach for evolutionary models of phenotypic traits on phylogeny. Evolution 67(2):355–367
Lajeunesse MJ (2009) Meta-analysis and the comparative phylogenetic method. Am Nat 174(3):369–381. doi:10.1086/603628
Legendre P, Lapointe FJ, Casgrain P (1994) Modeling brain evolution from behavior: a permutational regression approach. Evolution 48(5):1487–1499. doi:10.2307/2410243
Link WA, Barker RJ (2006) Model weights and the foundations of multimodel inference. Ecology 87:2626–2635
Lynch M (1991) Methods for the analysis of comparative data in evolutionary biology. Evolution 45(5):1065–1080
Martins EP (1996) Conducting phylogenetic comparative analyses when phylogeny is not known. Evolution 50:12–22
Martins EP, Hansen TF (1997) Phylogenies and the comparative method: a general approach to incorporating phylogenetic information into the analysis of interspecific data. Am Nat 149:646–667
Massart P (ed) (2007) Concentration inequalities and model selection: ecole d’eté de probabilités de Saint-Flour XXXIII - 2003. Springer, Berlin
Mundry R (2011) Issues in information theory-based statistical inference–a commentary from a frequentist’s perspective. Behav Ecol Sociobiol 65(1):57–68
Mundry R, Nunn CL (2008) Stepwise model fitting and statistical inference: turning noise into signal pollution. Am Nat 173:119–123
Nakagawa S, Hauber ME (2011) Great challenges with few subjects: Statistical strategies for neuroscientists. Neurosci Biobehav Rev 35(3):462–473
O’Meara BC, Ané C, Sanderson MJ, Wainwright PC (2006) Testing for different rates of continuous trait evolution using likelihood. Evolution 60(5):922–933. doi:10.1111/j.0014-3820.2006.tb01171.x
Pagel M (1999) Inferring the historical patterns of biological evolution. Nature 401:877–884
Pagel M, Meade A, Barker D (2004) Bayesian estimation of ancestral character states on phylogenies. Syst Biol 53(5):673–684
Pagel M, Meade A (2006) Bayesian analysis of correlated evolution of discrete characters by reversible-jump Markov chain Monte Carlo. Am Nat 167(6):808–825
Posada D, Buckley TR (2004) Model selection and model averaging in phylogenetics: advantages of Akaike information criterion and Bayesian approaches over likelihood ratio tests. Syst Biol 53(5):793–808. doi:10.1080/10635150490522304
R Development Core Team (2013) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. http://www.R-project.orgS
Rabosky DL (2006) Likelihood methods for detecting temporal shifts in diversification rates. Evolution 60(6):1152–1164
Ripplinger J, Sullivan J (2008) Does choice in model selection affect maximum likelihood analysis? Syst Biol 57(1):76–85. doi:10.1080/10635150801898920
Scales JA, King AA, Butler MA (2009) Running for your life or running for your dinner: what drives fiber-type evolution in lizard locomotor muscles? Am Nat 173:543–553
Schmidt D, Makalic E (2011) The behaviour of the Akaike information criterion when applied to non-nested sequences of models. In: Li J (ed) AI 2010: advances in artificial intelligence, vol 6464. Lecture Notes in Computer Science. Springer, Heidelberg, pp 223–232. doi:10.1007/978-3-642-17432-2_23
Stephens PA, Buskirk SW, Hayward GD, Del Rio CM (2005) Information theory and hypothesis testing: a call for pluralism. J Appl Ecol 42(1):4–12
Symonds MRE, Moussalli A (2011) A brief guide to model selection, multimodel inference and model averaging in behavioural ecology using Akaike’s information criterion. Behav Ecol Sociobiol 65(1):13–21
Terribile LC, Olalla-Tarraga MA, Diniz JAF, Rodriguez MA (2009) Ecological and evolutionary components of body size: geographic variation of venomous snakes at the global scale. Biol J Linn Soc 98(1):94–109
Thomas GH, Freckleton RP, Székely T (2006) Comparative analyses of the influence of developmental mode on phenotypic diversification rates in shorebirds. Proc Roy Soc B-Biol Sci 273(1594):1619–1624
von Hardenberg A, Gonzalez-Voyer A (2013) Disentangling evolutionary cause-effect relationships with phylogenetic confirmatory path analysis. Evolution 67(2):378–387. doi:10.1111/j.1558-5646.2012.01790.x
Whitmee S, Orme CDL (2013) Predicting dispersal distance in mammals: a trait-based approach. J Anim Ecol 82(1):211–221. doi:10.1111/j.1365-2656.2012.02030.x
Whittingham MJ, Stephens PA, Bradbury RB, Freckleton RP (2006) Why do we still use stepwise modelling in ecology and behaviour? J Anim Ecol 75:1182–1189
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Garamszegi, L.Z., Mundry, R. (2014). Multimodel-Inference in Comparative Analyses. In: Garamszegi, L. (eds) Modern Phylogenetic Comparative Methods and Their Application in Evolutionary Biology. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-43550-2_12
Download citation
DOI: https://doi.org/10.1007/978-3-662-43550-2_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-43549-6
Online ISBN: 978-3-662-43550-2
eBook Packages: Biomedical and Life SciencesBiomedical and Life Sciences (R0)