Please use this identifier to cite or link to this item:
https://doi.org/10.1016/j.spl.2013.02.005
DC Field | Value | |
---|---|---|
dc.title | Likelihood computation for hidden Markov models via generalized two-filter smoothing | |
dc.contributor.author | Persing, A. | |
dc.contributor.author | Jasra, A. | |
dc.date.accessioned | 2016-06-02T10:30:17Z | |
dc.date.available | 2016-06-02T10:30:17Z | |
dc.date.issued | 2013-05 | |
dc.identifier.citation | Persing, A., Jasra, A. (2013-05). Likelihood computation for hidden Markov models via generalized two-filter smoothing. Statistics and Probability Letters 83 (5) : 1433-1442. ScholarBank@NUS Repository. https://doi.org/10.1016/j.spl.2013.02.005 | |
dc.identifier.issn | 01677152 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/125056 | |
dc.description.abstract | We introduce an estimate for the likelihood of hidden Markov models (HMMs) using sequential Monte Carlo (SMC) approximations of the generalized two-filter smoothing decomposition (Briers etal., 2010). This estimate is unbiased and a central limit theorem (CLT) is established. The new estimate is also investigated from a numerical perspective. © 2013 Elsevier B.V. | |
dc.description.uri | http://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1016/j.spl.2013.02.005 | |
dc.source | Scopus | |
dc.subject | Generalized two-filter smoothing | |
dc.subject | Likelihood estimation | |
dc.subject | Sequential Monte Carlo | |
dc.type | Article | |
dc.contributor.department | STATISTICS & APPLIED PROBABILITY | |
dc.description.doi | 10.1016/j.spl.2013.02.005 | |
dc.description.sourcetitle | Statistics and Probability Letters | |
dc.description.volume | 83 | |
dc.description.issue | 5 | |
dc.description.page | 1433-1442 | |
dc.description.coden | SPLTD | |
dc.identifier.isiut | 000317808700018 | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.