The Neutral Population Model and Bayesian Nonparametrics
In this paper a widely-studied model in Population Genetics, the so-called Infinitely- Many-Alleles model with neutral mutation, is reinterpreted in terms of a timedependent Bayesian nonparametric statistical model, where the prior of the model is described by the Neutral Fleming-Viot process. A natural likelihood process is introduced such that every collection of k observations, at each time point, is essentially a vector of i.i.d. samples from the state of the Fleming-Viot process at that time. The dynamic properties of the particle process induced by such a likelihood are studied. The Moran model is derived as the marginal distribution of a timedependent sample induced by such a choice of prior and likelihood. The derivation of all results relies on the transition density of the Neutral Fleming-Viot process and on a new representation for the Dirichlet process.
|Date of creation:||Mar 2007|
|Date of revision:|
|Contact details of provider:|| Postal: Corso Unione Sovietica, 218bis - 10134 Torino - Italy|
Phone: +39 011 6706060
Fax: +39 011 6706060
Web page: http://www.esomas.unito.it/
More information through EDIRC
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Stephen G. Walker & Matteo Ruggiero, 2007. "Construction and Stationary Distribution of the Fleming-Viot Process with Viability Selection," ICER Working Papers - Applied Mathematics Series 14-2007, ICER - International Centre for Economic Research.
When requesting a correction, please mention this item's handle: RePEc:icr:wpmath:18-2007. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Simone Pellegrino)
If references are entirely missing, you can add them using this form.