Use this URL to cite or link to this record in EThOS: | https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.731397 |
![]() |
|||||||
Title: | The iterated auxiliary particle filter and applications to state space models and diffusion processes | ||||||
Author: | Guarniero, Pieralberto |
ISNI:
0000 0004 6496 5581
|
|||||
Awarding Body: | University of Warwick | ||||||
Current Institution: | University of Warwick | ||||||
Date of Award: | 2017 | ||||||
Availability of Full Text: |
|
||||||
Abstract: | |||||||
The novel research work presented in this thesis consists of an offline, iterated particle filter to facilitate statistical inference in general state space hidden Markov models. Given a model and a sequence of observations, the associated marginal likelihood L is central to likelihood-based inference for unknown statistical parameters. We define a class of “twisted” models: each member is specified by a sequence of positive functions ψ and has an associated ψ - auxiliary particle filter that provides unbiased estimates of L. We identify a sequence ψ* that is optimal in the sense that the ψ* -auxiliary particle filter’s estimate of L has zero variance. In practical applications, ψ* is unknown so the ψ* - auxiliary particle filter cannot straightforwardly be implemented. We use an iterative scheme to approximate ψ*, and demonstrate empirically that the resulting iterated auxiliary particle filter significantly outperforms the most popular competitors in some challenging settings. Applications include parameter estimation using a particle Markov chain Monte Carlo algorithm. An adaptation of the iAPF for statistical inference in the context of diffusion processes along with a number of examples and applications in this setting is provided.
|
|||||||
Supervisor: | Not available | Sponsor: | Not available | ||||
Qualification Name: | Thesis (Ph.D.) | Qualification Level: | Doctoral | ||||
EThOS ID: | uk.bl.ethos.731397 | DOI: | Not available | ||||
Keywords: | QA Mathematics | ||||||
Share: |