RAND Statistics Seminar Series

Analysis of Gene Expression Leukemia Data using Split-Merge Markov Chain Monte Carlo

Presented by Sonia Jain, Ph.D., University of California – San Diego
Thursday May 15, 2008
12:00 P.M. PT
Conference Room 1226 & 1228
RAND Corporation, Santa Monica, CA
Please contact Denise Miller if you would like to attend this seminar.


The inferential problem of associating data in high dimensions to mixture components is difficult when components are nearby or overlapping. We introduce a new split-merge Markov chain Monte Carlo technique that efficiently classifies observations by splitting and merging mixture components of a nonconjugate Bayesian mixture model. Our method, which is a Metropolis-Hastings procedure with split-merge proposals, samples clusters of observations simultaneously rather than incrementally assigning observations to mixture components. Split-merge moves are produced by exploiting properties of a restricted Gibbs sampling scan. We apply our split-merge technique to a cancer classification problem, in which patients are clustered according to leukemia type based on their gene expression data obtained from DNA microarray experiments.

Speaker Bio

Dr. Sonia Jain conducts methodological research in Biostatistics and Bioinformatics. She develops nonparametric Bayesian models and Markov chain Monte Carlo techniques for the analysis of high-dimensional data, as observed in the analysis of gene expression data obtained from DNA microarray experiments. In particular, Dr. Jain is interested in Bayesian mixture models and the flexibility they provide in modeling complex data structures. Dr. Jain's areas of expertise are: 1) Analysis of high-dimensional genomic data, e.g. microarray data; 2) Application of Bayesian methodology in Biostatistics; 3) Development of Markov chain Monte Carlo algorithms; 4) Model-based alternatives to exploratory statistical analysis.

Attending a Seminar

Other Locations/Times:
Washington, D.C. Conf. Rm. 4132: 3:00pm ET
Pittsburgh Conf. Rm. 6206: 3:00pm ET

RAND visitors are welcome to attend and must RSVP at least one day prior to the seminar. To ensure your attendance please contact Denise Miller at dmiller@rand.org with your name, company (or university) affiliation, and national citizenship (for security purposes).

For parking and directions to RAND's Santa Monica office, please see: http://www.rand.org/about/locations/santa-monica.html.

For parking and directions to RAND's Pittsburgh office, please see: http://www.rand.org/about/locations/pittsburgh.html.

For further information and to be added to the mailing list contact Denise Miller at dmiller@rand.org.