schliessen

Filtern

 

Bibliotheken

Multivariate Phylogenetic Comparative Methods: Evaluations, Comparisons, and Recommendations

Abstract Recent years have seen increased interest in phylogenetic comparative analyses of multivariate data sets, but to date the varied proposed approaches have not been extensively examined. Here we review the mathematical properties required of any multivariate method, and specifically evaluate... Full description

Journal Title: Systematic biology 2018-01-01, Vol.67 (1), p.14-31
Main Author: Adams, Dean C
Other Authors: Collyer, Michael L
Format: Electronic Article Electronic Article
Language: English
Subjects:
Publisher: England: Oxford University Press
ID: ISSN: 1063-5157
Link: https://www.ncbi.nlm.nih.gov/pubmed/28633306
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: cdi_proquest_miscellaneous_1912195661
title: Multivariate Phylogenetic Comparative Methods: Evaluations, Comparisons, and Recommendations
format: Article
creator:
  • Adams, Dean C
  • Collyer, Michael L
subjects:
  • Classification
  • Comparative analysis
  • Computer Simulation
  • Data processing
  • Datasets
  • Evolution
  • Mathematical models
  • Mathematics
  • Matrix
  • Models, Biological
  • Multivariate Analysis
  • Phylogenetics
  • Phylogeny
  • Principal components analysis
  • Statistics
ispartof: Systematic biology, 2018-01-01, Vol.67 (1), p.14-31
description: Abstract Recent years have seen increased interest in phylogenetic comparative analyses of multivariate data sets, but to date the varied proposed approaches have not been extensively examined. Here we review the mathematical properties required of any multivariate method, and specifically evaluate existing multivariate phylogenetic comparative methods in this context. Phylogenetic comparative methods based on the full multivariate likelihood are robust to levels of covariation among trait dimensions and are insensitive to the orientation of the data set, but display increasing model misspecification as the number of trait dimensions increases. This is because the expected evolutionary covariance matrix (V) used in the likelihood calculations becomes more ill-conditioned as trait dimensionality increases, and as evolutionary models become more complex. Thus, these approaches are only appropriate for data sets with few traits and many species. Methods that summarize patterns across trait dimensions treated separately (e.g., SURFACE) incorrectly assume independence among trait dimensions, resulting in nearly a 100% model misspecification rate. Methods using pairwise composite likelihood are highly sensitive to levels of trait covariation, the orientation of the data set, and the number of trait dimensions. The consequences of these debilitating deficiencies are that a user can arrive at differing statistical conclusions, and therefore biological inferences, simply from a dataspace rotation, like principal component analysis. By contrast, algebraic generalizations of the standard phylogenetic comparative toolkit that use the trace of covariance matrices are insensitive to levels of trait covariation, the number of trait dimensions, and the orientation of the data set. Further, when appropriate permutation tests are used, these approaches display acceptable Type I error and statistical power. We conclude that methods summarizing information across trait dimensions, as well as pairwise composite likelihood methods should be avoided, whereas algebraic generalizations of the phylogenetic comparative toolkit provide a useful means of assessing macroevolutionary patterns in multivariate data. Finally, we discuss areas in which multivariate phylogenetic comparative methods are still in need of future development; namely highly multivariate Ornstein–Uhlenbeck models and approaches for multivariate evolutionary model comparisons.
language: eng
source:
identifier: ISSN: 1063-5157
fulltext: no_fulltext
issn:
  • 1063-5157
  • 1076-836X
url: Link


@attributes
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
RANK2.750616
LOCALfalse
PrimoNMBib
record
control
sourceidproquest_opena
recordidTN_cdi_proquest_miscellaneous_1912195661
sourceformatXML
sourcesystemPC
oup_id10.1093/sysbio/syx055
sourcerecordid1912195661
originalsourceidFETCH-LOGICAL-1469t-853e781d450ca5ee6382bab2d309b1d204e529a493dcd9e9339ebf8445681b4c0
addsrcrecordideNqFkctrFjEUxYMo9qFLtzLgxoVT85hkEnfyUaulRREFF0LI445NmZlMk5nS77837XztoiCubnLz43BODkKvCD4iWLH3eZttiGXcYM6foH2CW1FLJn49vT0LVnPC2z10kPMlxoQITp6jPSoFYwyLffT7fOnncG1SMDNU3y62ffwDI8zBVZs4TCaZ8grVOcwX0ecP1fG16Zeyi2N-tyNCvruY0VffwcVhgNGvxAv0rDN9hpe7eYh-fjr-sflcn309-bL5eFaTRqi5lpxBK4lvOHaGAwgmqTWWeoaVJZ7iBjhVplHMO69AMabAdrJpuJDENg4fotNVN04wmpBATykMJm11NEH7EkcXR8aFGXQnQXkAK1tlpbcdVwYb6aQjbSctyCL2dhWbUrxaIM96CNlB35sR4pI1UYQSxYUgBX3zCL2MSxpL1EIpSgVtcVuoeqVcijkn6B7cEaxvO9Rrh3rtsPCvd6qLHcA_0PelFYA9EizJ7n58Tib0_5Td5YrL9B8HfwF4C7t8
sourcetypeOpen Access Repository
isCDItrue
recordtypearticle
pqid1992262707
display
typearticle
titleMultivariate Phylogenetic Comparative Methods: Evaluations, Comparisons, and Recommendations
creatorAdams, Dean C ; Collyer, Michael L
creatorcontribAdams, Dean C ; Collyer, Michael L
descriptionAbstract Recent years have seen increased interest in phylogenetic comparative analyses of multivariate data sets, but to date the varied proposed approaches have not been extensively examined. Here we review the mathematical properties required of any multivariate method, and specifically evaluate existing multivariate phylogenetic comparative methods in this context. Phylogenetic comparative methods based on the full multivariate likelihood are robust to levels of covariation among trait dimensions and are insensitive to the orientation of the data set, but display increasing model misspecification as the number of trait dimensions increases. This is because the expected evolutionary covariance matrix (V) used in the likelihood calculations becomes more ill-conditioned as trait dimensionality increases, and as evolutionary models become more complex. Thus, these approaches are only appropriate for data sets with few traits and many species. Methods that summarize patterns across trait dimensions treated separately (e.g., SURFACE) incorrectly assume independence among trait dimensions, resulting in nearly a 100% model misspecification rate. Methods using pairwise composite likelihood are highly sensitive to levels of trait covariation, the orientation of the data set, and the number of trait dimensions. The consequences of these debilitating deficiencies are that a user can arrive at differing statistical conclusions, and therefore biological inferences, simply from a dataspace rotation, like principal component analysis. By contrast, algebraic generalizations of the standard phylogenetic comparative toolkit that use the trace of covariance matrices are insensitive to levels of trait covariation, the number of trait dimensions, and the orientation of the data set. Further, when appropriate permutation tests are used, these approaches display acceptable Type I error and statistical power. We conclude that methods summarizing information across trait dimensions, as well as pairwise composite likelihood methods should be avoided, whereas algebraic generalizations of the phylogenetic comparative toolkit provide a useful means of assessing macroevolutionary patterns in multivariate data. Finally, we discuss areas in which multivariate phylogenetic comparative methods are still in need of future development; namely highly multivariate Ornstein–Uhlenbeck models and approaches for multivariate evolutionary model comparisons.
identifier
0ISSN: 1063-5157
1EISSN: 1076-836X
2DOI: 10.1093/sysbio/syx055
3PMID: 28633306
languageeng
publisherEngland: Oxford University Press
subjectClassification ; Comparative analysis ; Computer Simulation ; Data processing ; Datasets ; Evolution ; Mathematical models ; Mathematics ; Matrix ; Models, Biological ; Multivariate Analysis ; Phylogenetics ; Phylogeny ; Principal components analysis ; Statistics
ispartofSystematic biology, 2018-01-01, Vol.67 (1), p.14-31
rights
0The Author(s) 2017. Published by Oxford University Press on behalf of the Systematic Biology. All rights reserved. For Permissions, please email: journals.permissions@oup.com 2017
1The Author(s) 2017. Published by Oxford University Press on behalf of the Systematic Biology. All rights reserved. For Permissions, please email: journals.permissions@oup.com.
lds50peer_reviewed
oafree_for_read
citedbyFETCH-LOGICAL-1469t-853e781d450ca5ee6382bab2d309b1d204e529a493dcd9e9339ebf8445681b4c0
citesFETCH-LOGICAL-1469t-853e781d450ca5ee6382bab2d309b1d204e529a493dcd9e9339ebf8445681b4c0
links
openurl$$Topenurl_article
thumbnail$$Usyndetics_thumb_exl
backlink$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/28633306$$D View this record in MEDLINE/PubMed
search
creatorcontrib
0Adams, Dean C
1Collyer, Michael L
title
0Multivariate Phylogenetic Comparative Methods: Evaluations, Comparisons, and Recommendations
1Systematic biology
addtitleSyst Biol
descriptionAbstract Recent years have seen increased interest in phylogenetic comparative analyses of multivariate data sets, but to date the varied proposed approaches have not been extensively examined. Here we review the mathematical properties required of any multivariate method, and specifically evaluate existing multivariate phylogenetic comparative methods in this context. Phylogenetic comparative methods based on the full multivariate likelihood are robust to levels of covariation among trait dimensions and are insensitive to the orientation of the data set, but display increasing model misspecification as the number of trait dimensions increases. This is because the expected evolutionary covariance matrix (V) used in the likelihood calculations becomes more ill-conditioned as trait dimensionality increases, and as evolutionary models become more complex. Thus, these approaches are only appropriate for data sets with few traits and many species. Methods that summarize patterns across trait dimensions treated separately (e.g., SURFACE) incorrectly assume independence among trait dimensions, resulting in nearly a 100% model misspecification rate. Methods using pairwise composite likelihood are highly sensitive to levels of trait covariation, the orientation of the data set, and the number of trait dimensions. The consequences of these debilitating deficiencies are that a user can arrive at differing statistical conclusions, and therefore biological inferences, simply from a dataspace rotation, like principal component analysis. By contrast, algebraic generalizations of the standard phylogenetic comparative toolkit that use the trace of covariance matrices are insensitive to levels of trait covariation, the number of trait dimensions, and the orientation of the data set. Further, when appropriate permutation tests are used, these approaches display acceptable Type I error and statistical power. We conclude that methods summarizing information across trait dimensions, as well as pairwise composite likelihood methods should be avoided, whereas algebraic generalizations of the phylogenetic comparative toolkit provide a useful means of assessing macroevolutionary patterns in multivariate data. Finally, we discuss areas in which multivariate phylogenetic comparative methods are still in need of future development; namely highly multivariate Ornstein–Uhlenbeck models and approaches for multivariate evolutionary model comparisons.
subject
0Classification
1Comparative analysis
2Computer Simulation
3Data processing
4Datasets
5Evolution
6Mathematical models
7Mathematics
8Matrix
9Models, Biological
10Multivariate Analysis
11Phylogenetics
12Phylogeny
13Principal components analysis
14Statistics
issn
01063-5157
11076-836X
fulltextfalse
rsrctypearticle
creationdate2018
recordtypearticle
recordideNqFkctrFjEUxYMo9qFLtzLgxoVT85hkEnfyUaulRREFF0LI445NmZlMk5nS77837XztoiCubnLz43BODkKvCD4iWLH3eZttiGXcYM6foH2CW1FLJn49vT0LVnPC2z10kPMlxoQITp6jPSoFYwyLffT7fOnncG1SMDNU3y62ffwDI8zBVZs4TCaZ8grVOcwX0ecP1fG16Zeyi2N-tyNCvruY0VffwcVhgNGvxAv0rDN9hpe7eYh-fjr-sflcn309-bL5eFaTRqi5lpxBK4lvOHaGAwgmqTWWeoaVJZ7iBjhVplHMO69AMabAdrJpuJDENg4fotNVN04wmpBATykMJm11NEH7EkcXR8aFGXQnQXkAK1tlpbcdVwYb6aQjbSctyCL2dhWbUrxaIM96CNlB35sR4pI1UYQSxYUgBX3zCL2MSxpL1EIpSgVtcVuoeqVcijkn6B7cEaxvO9Rrh3rtsPCvd6qLHcA_0PelFYA9EizJ7n58Tib0_5Td5YrL9B8HfwF4C7t8
startdate20180101
enddate20180101
creator
0Adams, Dean C
1Collyer, Michael L
general
0Oxford University Press
1Oxford University Press (OUP)
scope
0CGR
1CUY
2CVF
3ECM
4EIF
5NPM
6AAYXX
7CITATION
8K9.
97X8
10CLFQK
sort
creationdate20180101
titleMultivariate Phylogenetic Comparative Methods: Evaluations, Comparisons, and Recommendations
authorAdams, Dean C ; Collyer, Michael L
facets
frbrtype5
frbrgroupidcdi_FETCH-LOGICAL-1469t-853e781d450ca5ee6382bab2d309b1d204e529a493dcd9e9339ebf8445681b4c0
rsrctypearticles
prefilterarticles
languageeng
creationdate2018
topic
0Classification
1Comparative analysis
2Computer Simulation
3Data processing
4Datasets
5Evolution
6Mathematical models
7Mathematics
8Matrix
9Models, Biological
10Multivariate Analysis
11Phylogenetics
12Phylogeny
13Principal components analysis
14Statistics
toplevelpeer_reviewed
creatorcontrib
0Adams, Dean C
1Collyer, Michael L
collection
0Medline
1MEDLINE
2MEDLINE (Ovid)
3MEDLINE
4MEDLINE
5PubMed
6CrossRef
7ProQuest Health & Medical Complete (Alumni)
8MEDLINE - Academic
9OpenAIRE
jtitleSystematic biology
delivery
delcategoryRemote Search Resource
fulltextno_fulltext
addata
au
0Adams, Dean C
1Collyer, Michael L
formatjournal
genrearticle
ristypeJOUR
atitleMultivariate Phylogenetic Comparative Methods: Evaluations, Comparisons, and Recommendations
jtitleSystematic biology
addtitleSyst Biol
date2018-01-01
risdate2018
volume67
issue1
spage14
epage31
pages14-31
issn1063-5157
eissn1076-836X
abstractAbstract Recent years have seen increased interest in phylogenetic comparative analyses of multivariate data sets, but to date the varied proposed approaches have not been extensively examined. Here we review the mathematical properties required of any multivariate method, and specifically evaluate existing multivariate phylogenetic comparative methods in this context. Phylogenetic comparative methods based on the full multivariate likelihood are robust to levels of covariation among trait dimensions and are insensitive to the orientation of the data set, but display increasing model misspecification as the number of trait dimensions increases. This is because the expected evolutionary covariance matrix (V) used in the likelihood calculations becomes more ill-conditioned as trait dimensionality increases, and as evolutionary models become more complex. Thus, these approaches are only appropriate for data sets with few traits and many species. Methods that summarize patterns across trait dimensions treated separately (e.g., SURFACE) incorrectly assume independence among trait dimensions, resulting in nearly a 100% model misspecification rate. Methods using pairwise composite likelihood are highly sensitive to levels of trait covariation, the orientation of the data set, and the number of trait dimensions. The consequences of these debilitating deficiencies are that a user can arrive at differing statistical conclusions, and therefore biological inferences, simply from a dataspace rotation, like principal component analysis. By contrast, algebraic generalizations of the standard phylogenetic comparative toolkit that use the trace of covariance matrices are insensitive to levels of trait covariation, the number of trait dimensions, and the orientation of the data set. Further, when appropriate permutation tests are used, these approaches display acceptable Type I error and statistical power. We conclude that methods summarizing information across trait dimensions, as well as pairwise composite likelihood methods should be avoided, whereas algebraic generalizations of the phylogenetic comparative toolkit provide a useful means of assessing macroevolutionary patterns in multivariate data. Finally, we discuss areas in which multivariate phylogenetic comparative methods are still in need of future development; namely highly multivariate Ornstein–Uhlenbeck models and approaches for multivariate evolutionary model comparisons.
copEngland
pubOxford University Press
pmid28633306
doi10.1093/sysbio/syx055
oafree_for_read