Particle filter-based approximate maximum likelihood inference asymptotics in state-space models
ESAIM. Proceedings, Tome 19 (2007), pp. 115-120
To implement maximum likelihood estimation in state-space models, the log-likelihood function must be approximated. We study such approximations based on particle filters, and in particular conditions for consistency of the corresponding approximate maximum likelihood estimator. Numerical results illustrate the theory.
@article{EP_2007_19_a15,
author = {Jimmy Olsson and Tobias Ryd\'en},
title = {Particle filter-based approximate maximum likelihood inference asymptotics in state-space models},
journal = {ESAIM. Proceedings},
pages = {115--120},
year = {2007},
volume = {19},
doi = {10.1051/proc:071915},
language = {en},
url = {http://geodesic.mathdoc.fr/articles/10.1051/proc:071915/}
}
TY - JOUR AU - Jimmy Olsson AU - Tobias Rydén TI - Particle filter-based approximate maximum likelihood inference asymptotics in state-space models JO - ESAIM. Proceedings PY - 2007 SP - 115 EP - 120 VL - 19 UR - http://geodesic.mathdoc.fr/articles/10.1051/proc:071915/ DO - 10.1051/proc:071915 LA - en ID - EP_2007_19_a15 ER -
%0 Journal Article %A Jimmy Olsson %A Tobias Rydén %T Particle filter-based approximate maximum likelihood inference asymptotics in state-space models %J ESAIM. Proceedings %D 2007 %P 115-120 %V 19 %U http://geodesic.mathdoc.fr/articles/10.1051/proc:071915/ %R 10.1051/proc:071915 %G en %F EP_2007_19_a15
Jimmy Olsson; Tobias Rydén. Particle filter-based approximate maximum likelihood inference asymptotics in state-space models. ESAIM. Proceedings, Tome 19 (2007), pp. 115-120. doi: 10.1051/proc:071915
Cité par Sources :