| EPSRC Reference: |
GR/R22322/01 |
| Title: |
Approximate Approaches To Likelihood and Bayesian Statistical Inference In Incomplete-Data Problems |
| Principal Investigator: |
Titterington, Professor DM |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Statistics |
| Organisation: |
University of Glasgow |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
15 March 2002 |
Ends: |
14 March 2005 |
Value (£): |
143,463
|
| EPSRC Research Topic Classifications: |
| Statistics & Appl. Probability |
|
|
| EPSRC Industrial Sector Classifications: |
| Information Technologies |
No relevance to Underpinning Sectors |
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
Maximum likelihood and Bayesian inference are nontrivial in incomplete data problems, for computational reasons. Often even the EM algorithum is difficult, and approximations to the E-step are needed to make the procedure tractable. For instance, a complicated E-step can be approximated using independence models (Mean-field approximations). Independence models are also the key to providing both lower bounds to the loglikelihood of interest, thereby affording a more direct source of approximate inference, and so-called variational approximations to Bayesian posterior distributions. Although these mehods have been used quite widely in the recent neural-computing literature, much remains to be discovered about their properties in general. This project will investigate these issues, for both these independence-model approximations and refinements thereof that remain fairly tractable but do reflect some of the correlations that the independence models neglect. A deliberate effort will be made to inform th emainstream statistical community about these types of approximation, reported so far almost exclusively in other literatures.
|
|
Key Findings |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Potential use in non-academic contexts |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Impacts |
|
| Description |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk |
| Summary |
|
| Date Materialised |
|
|
|
|
Sectors submitted by the Researcher |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
| Project URL: |
|
| Further Information: |
|
| Organisation Website: |
http://www.gla.ac.uk |