Hi everybody, I have a few questions about interpreting the output of the threhsBayes function in phytools. Let’s suppose we have a negative correlation between a continuous (e.g., body size) and a discrete trait, and the output shows:
Mean correlation from the posterior sample: -0.43 Ordination of discrete traits: Trait 2: 0 <-> 1 Does the “ordination of discrete traits” imply any directionality between the states of the discrete variable? For example, does the negative correlation mean larger species are less likely to change from 0 to 1? If so, does it also mean larger species are more likely to change from 1 to 0? Perhaps, a similar interpretation can be found in this paper: https://doi.org/10.1111/evo.13657 “The posterior distribution of the Bayesian threshold model had an average correlation coefficient between parity mode and temperature of −0.63 (95% HPD: −0.4, −0.83), indicating strong support for a negative correlation between viviparity and temperature, where viviparity is associated to colder climates and oviparity to warmer climates (Supporting Information Fig. S4).” An alternative interpretation would be that transitions between 0 and 1 (in both directions) are more likely to occur among smaller species. Are any of these interpretations correct? Thank you! Stenio I. A. Foerster Department of Zoology University of Tartu (Tartu, Estonia) CV<https://www.etis.ee/CV/foersterst/eng> | ORCID<https://orcid.org/0000-0001-9639-9009> | RG<https://www.researchgate.net/profile/Stenio_Foerster2> | Lattes<http://lattes.cnpq.br/0589282540409945> [[alternative HTML version deleted]] _______________________________________________ R-sig-phylo mailing list - R-sig-phylo@r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-phylo Searchable archive at http://www.mail-archive.com/r-sig-phylo@r-project.org/
