Note to users. If you're seeing this message, it means that your browser cannot find this page's style/presentation instructions -- or possibly that you are using a browser that does not support current Web standards. Find out more about why this message is appearing, and what you can do to make your experience of our site the best it can be.

Science 21 April 2006:
Vol. 312. no. 5772, p. 367
DOI: 10.1126/science.1123622
Prev | Table of Contents | Next

Technical Comments

Comment on "Phylogenetic MCMC Algorithms Are Misleading on Mixtures of Trees"

Fredrik Ronquist1*, Bret Larget2, John P. Huelsenbeck3, Joseph B. Kadane4, Donald Simon5 and Paul van der Mark1

1 School of Computational Science, Florida State University, Tallahassee, FL 32306–4120, USA.
2 Department of Statistics, University of Wisconsin, Madison, WI 53706, USA.
3 Division of Biological Sciences, University of California at San Diego, San Diego, CA 92093–0116, USA.
4 Department of Statistics, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
5 Department of Mathematics and Computer Science, Duquesne University, Pittsburgh, PA 15282, USA.


Figure 1 Fig. 1. We generated 10,000 binary characters on the mixture described by Mossel and Vigoda (five tips; a = 0.1) and compared tree samples from 20 independent MCMC runs (average standard deviation of partition frequencies). The slow mixing of naive MCMC implementations is readily detected (upper two curves) and disappears when using more standard MCMC schemes or when the model misspecification is corrected (lower three curves). Similar results were obtained when sampling from the expectation of the posterior. [View Larger Version of this Image (25K GIF file)]
 

To Advertise     Find Products

Science. ISSN 0036-8075 (print), 1095-9203 (online)