We consider continuous-time models where the observed process depends on an unobserved jump Markov Process. We develop a sequential Monte Carlo algorithm which makes it possible to filter and smooth this latent process, and compute the likelihood pointwise. We develop a Rao-Blackwellisation technique which allows to significantly reduce the Monte Carlo noise of this algorithm. Possible extensions of our algorithm and further directions of research are discussed.
Particle filtering for continuous-time hidden Markov models
Varini E
2007
Abstract
We consider continuous-time models where the observed process depends on an unobserved jump Markov Process. We develop a sequential Monte Carlo algorithm which makes it possible to filter and smooth this latent process, and compute the likelihood pointwise. We develop a Rao-Blackwellisation technique which allows to significantly reduce the Monte Carlo noise of this algorithm. Possible extensions of our algorithm and further directions of research are discussed.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.