tag:blogger.com,1999:blog-7959705296201073323.post5769729243937395486..comments2023-02-24T11:14:00.053+01:00Comments on The Bayesian kitchen: Bayesian priors for diversification studiesAnonymoushttp://www.blogger.com/profile/09710797049914216414noreply@blogger.comBlogger3125tag:blogger.com,1999:blog-7959705296201073323.post-76207074623603834942014-11-13T19:27:00.934+01:002014-11-13T19:27:00.934+01:00I have rephrased the argument (next post)... I hop...I have rephrased the argument (next post)... I hope this clarifies.<br /><br />N.Anonymoushttps://www.blogger.com/profile/09710797049914216414noreply@blogger.comtag:blogger.com,1999:blog-7959705296201073323.post-5370481780934128032014-11-13T18:13:38.075+01:002014-11-13T18:13:38.075+01:00Hi Gilles,
yes, the phi is the same.
without any...Hi Gilles,<br /><br />yes, the phi is the same.<br /><br />without any conditioning:<br /><br />repeat<br /> Nature chooses theta from phi<br /> Nature runs diversification process given theta<br />until process survives<br /><br />gives you theta from p(theta | S) (the conditional prior)<br /><br />Now, if you also condition on observed tree T:<br /><br />repeat<br /> Nature chooses theta from phi<br /> Nature runs diversification process given theta<br />until process survives AND simulated phylogeny matches observed phylogeny<br /><br />then you sample theta from equation 1, right? (perhaps I should have made the actual conditioning on observed T explicit in my notation).<br /><br />Or are you referring to something else?<br /><br />Anonymoushttps://www.blogger.com/profile/09710797049914216414noreply@blogger.comtag:blogger.com,1999:blog-7959705296201073323.post-73089646002812938562014-11-13T17:53:33.051+01:002014-11-13T17:53:33.051+01:00Hi,
I certainly miss something but the $\theta$&#...Hi,<br /><br />I certainly miss something but the $\theta$'s drawn from your algorithmic model are not $\phi$-distributed anymore (their actual distribution may be derived from $\phi$). Is the $phi$ of your equation 1 the same as in the beginning of your text?<br /><br />Cheers<br /><br />Gilles DidierAnonymousnoreply@blogger.com