The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Online Program Home
Abstract Details
Activity Number:
|
485
|
Type:
|
Invited
|
Date/Time:
|
Wednesday, August 1, 2012 : 10:30 AM to 12:20 PM
|
Sponsor:
|
SSC
|
Abstract - #303792 |
Title:
|
Clustering and Biclustering of Relational Data
|
Author(s):
|
Alejandro Murua*+ and Thierry Chekouo Tekougang
|
Companies:
|
Université de Montréal and Université de Montréal
|
Address:
|
, , ,
|
Keywords:
|
clustering ;
biclustering ;
auto-logistic model ;
Bayesian plaid model ;
gene expression ;
deviance information criterion
|
Abstract:
|
In many applications the data points interdependence may be complex. We suppose that this can be modeled through a relational graph. The strength of the dependence between points is given by the graph edge weights. For example, when analyzing gene expression data, the genes interdependence may be given by their common ontologies. The data clustering or biclustering must obey the constraints of the point relationships. In this work, we introduce a biclustering model that takes into account the data point relationships. These are modeled by imposing an auto-logistic prior on the vertices of the relational graph. The biclustering model is given by a Bayesian Plaid-type model. We also present a modified DIC criterion to choose the appropriate number of biclusters. We show some applications of our ideas to gene expression data. We note that very few statistical models for biclustering have been proposed in the literature. Instead, most of the research has focused on algorithms to find biclusters.
|
The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.
Back to the full JSM 2012 program
|
2012 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.