Estimation of discrete partially directed acyclic graphical models in multitype branching processes

We address the inference of discrete-state models for tree-structured data. Our aims is to introduce parametric multitype branching processes that can be efficiently estimated on the basis of data of limited size. Each generation distribution within this macroscopic model is modeled by a partially directed acyclic graphical model. The estimation of each graphical model relies on a greedy algorithm for graph selection. We present an algorithm for discrete graphical model which is applied on multivariate count data. The proposed modeling approach is illustrated on plant architecture datasets.

Bibliographic Details

Main Authors:	Fernique, Pierre, Durand, Jean-Baptiste, Guédon, Yann
Format:	conference_item biblioteca
Language:	eng
Published:	s.n.
Subjects:	U10 - Informatique, mathématiques et statistiques, F50 - Anatomie et morphologie des plantes, F62 - Physiologie végétale - Croissance et développement,
Online Access:	http://agritrop.cirad.fr/574649/ http://agritrop.cirad.fr/574649/1/document_574649.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!