FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4321476882> ?p ?o ?g. }

• W4321476882 endingPage "638" @default.
• W4321476882 startingPage "616" @default.
• W4321476882 abstract "Abstract There is still no consensus as to how to select models in Bayesian phylogenetics, and more generally in applied Bayesian statistics. Bayes factors are often presented as the method of choice, yet other approaches have been proposed, such as cross-validation or information criteria. Each of these paradigms raises specific computational challenges, but they also differ in their statistical meaning, being motivated by different objectives: either testing hypotheses or finding the best-approximating model. These alternative goals entail different compromises, and as a result, Bayes factors, cross-validation, and information criteria may be valid for addressing different questions. Here, the question of Bayesian model selection is revisited, with a focus on the problem of finding the best-approximating model. Several model selection approaches were re-implemented, numerically assessed and compared: Bayes factors, cross-validation (CV), in its different forms (k-fold or leave-one-out), and the widely applicable information criterion (wAIC), which is asymptotically equivalent to leave-one-out cross-validation (LOO-CV). Using a combination of analytical results and empirical and simulation analyses, it is shown that Bayes factors are unduly conservative. In contrast, CV represents a more adequate formalism for selecting the model returning the best approximation of the data-generating process and the most accurate estimates of the parameters of interest. Among alternative CV schemes, LOO-CV and its asymptotic equivalent represented by the wAIC, stand out as the best choices, conceptually and computationally, given that both can be simultaneously computed based on standard Markov chain Monte Carlo runs under the posterior distribution. [Bayes factor; cross-validation; marginal likelihood; model comparison; wAIC.]" @default.
• W4321476882 created "2023-02-23" @default.
• W4321476882 creator A5057909697 @default.
• W4321476882 date "2023-02-22" @default.
• W4321476882 modified "2023-10-09" @default.
• W4321476882 title "Identifying the Best Approximating Model in Bayesian Phylogenetics: Bayes Factors, Cross-Validation or wAIC?" @default.
• W4321476882 cites W1499861606 @default.
• W4321476882 cites W1542258599 @default.
• W4321476882 cites W1571413698 @default.
• W4321476882 cites W1611975802 @default.
• W4321476882 cites W1841429278 @default.
• W4321476882 cites W1966827292 @default.
• W4321476882 cites W1967396577 @default.
• W4321476882 cites W1981251392 @default.
• W4321476882 cites W1983368215 @default.
• W4321476882 cites W1983408155 @default.
• W4321476882 cites W1985054565 @default.
• W4321476882 cites W1988520084 @default.
• W4321476882 cites W1996356638 @default.
• W4321476882 cites W2004514718 @default.
• W4321476882 cites W2012644626 @default.
• W4321476882 cites W2015558203 @default.
• W4321476882 cites W2016053029 @default.
• W4321476882 cites W2017519756 @default.
• W4321476882 cites W2019448438 @default.
• W4321476882 cites W2033872649 @default.
• W4321476882 cites W2055505622 @default.
• W4321476882 cites W2057765075 @default.
• W4321476882 cites W2060512257 @default.
• W4321476882 cites W2062018285 @default.
• W4321476882 cites W2063068713 @default.
• W4321476882 cites W2081724349 @default.
• W4321476882 cites W2094206246 @default.
• W4321476882 cites W2097977090 @default.
• W4321476882 cites W2098538101 @default.
• W4321476882 cites W2098998255 @default.
• W4321476882 cites W2101546326 @default.
• W4321476882 cites W2103601574 @default.
• W4321476882 cites W2104398544 @default.
• W4321476882 cites W2104891575 @default.
• W4321476882 cites W2118048521 @default.
• W4321476882 cites W2122035212 @default.
• W4321476882 cites W2127148540 @default.
• W4321476882 cites W2130902307 @default.
• W4321476882 cites W2131527832 @default.
• W4321476882 cites W2133585817 @default.
• W4321476882 cites W2136096754 @default.
• W4321476882 cites W2136847298 @default.
• W4321476882 cites W2142258617 @default.
• W4321476882 cites W2142499192 @default.
• W4321476882 cites W2142635246 @default.
• W4321476882 cites W2145311867 @default.
• W4321476882 cites W2147307434 @default.
• W4321476882 cites W2151257151 @default.
• W4321476882 cites W2152298208 @default.
• W4321476882 cites W2153882688 @default.
• W4321476882 cites W2158878884 @default.
• W4321476882 cites W2160634817 @default.
• W4321476882 cites W2162041430 @default.
• W4321476882 cites W2162250327 @default.
• W4321476882 cites W2163627198 @default.
• W4321476882 cites W2171142493 @default.
• W4321476882 cites W2185492685 @default.
• W4321476882 cites W2203714058 @default.
• W4321476882 cites W2292751606 @default.
• W4321476882 cites W2563867946 @default.
• W4321476882 cites W2597136739 @default.
• W4321476882 cites W2779290241 @default.
• W4321476882 cites W2792381687 @default.
• W4321476882 cites W2963732842 @default.
• W4321476882 cites W2987894624 @default.
• W4321476882 cites W3081516476 @default.
• W4321476882 cites W3101813170 @default.
• W4321476882 cites W3124230025 @default.
• W4321476882 cites W3132251092 @default.
• W4321476882 cites W4211177544 @default.
• W4321476882 cites W4232632925 @default.
• W4321476882 cites W4249297864 @default.
• W4321476882 cites W4249991467 @default.
• W4321476882 cites W4303453945 @default.
• W4321476882 doi "https://doi.org/10.1093/sysbio/syad004" @default.
• W4321476882 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36810802" @default.
• W4321476882 hasPublicationYear "2023" @default.
• W4321476882 type Work @default.
• W4321476882 citedByCount "2" @default.
• W4321476882 countsByYear W43214768822023 @default.
• W4321476882 crossrefType "journal-article" @default.
• W4321476882 hasAuthorship W4321476882A5057909697 @default.
• W4321476882 hasBestOaLocation W43214768821 @default.
• W4321476882 hasConcept C101112237 @default.
• W4321476882 hasConcept C105795698 @default.
• W4321476882 hasConcept C107673813 @default.
• W4321476882 hasConcept C111350023 @default.
• W4321476882 hasConcept C11413529 @default.
• W4321476882 hasConcept C119857082 @default.
• W4321476882 hasConcept C142291917 @default.
• W4321476882 hasConcept C149782125 @default.
• W4321476882 hasConcept C154945302 @default.

• next