Back to Search
Start Over
Mod\`ele \`a processus latent et algorithme EM pour la r\'egression non lin\'eaire
- Source :
- Revue des Nouvelles Technologies de l'Information (RNTI), Statistique et nouvelles technologies de l'information (2011) 15-32
- Publication Year :
- 2013
-
Abstract
- A non linear regression approach which consists of a specific regression model incorporating a latent process, allowing various polynomial regression models to be activated preferentially and smoothly, is introduced in this paper. The model parameters are estimated by maximum likelihood performed via a dedicated expecation-maximization (EM) algorithm. An experimental study using simulated and real data sets reveals good performances of the proposed approach.
Details
- Database :
- arXiv
- Journal :
- Revue des Nouvelles Technologies de l'Information (RNTI), Statistique et nouvelles technologies de l'information (2011) 15-32
- Publication Type :
- Report
- Accession number :
- edsarx.1312.6978
- Document Type :
- Working Paper