Award details

Statistical and stochastic modelling of complex biological processes with emphasis on spatial and temporal processes

Reference	BBS/E/C/00144035
Principal Investigator / Supervisor	Professor Robin Thompson
Co-Investigators / Co-Supervisors
Institution	Rothamsted Research
Department	Rothamsted Research Department
Funding type	Research
Value (£)	80,355
Status	Completed
Type	Institute Project
Start date	01/04/1997
End date	31/03/1999
Duration	24 months

Abstract

Research into areas of biometry, applied statistics and mathematical modelling that underpin agricultural research. This includes experimental design, generalised linear models, multivariate methods and non-linear inference. This work is stimulated by research problems in the Institute. One important theme is research into statistical and stochastic mathematical modelling, particularly involving spatial, temporal and multivariate aspects of biological processes. Objectives 1996 In the area of design and analysis of experiments: 1. Development of algorithms for constructing factorial experiments when there are multiple error strata and constraints on aliasing of model terms; 2. Construction of pseudo-factors associated with these designs; 3. Construction of designs taking into account correlation between observations; 4. Extension of generalized linear models to take account of correlation; 5. Improvement of existing estimation procedures, including using sampling assisted inference for correlated observations; 6. Extension of spectral techniques to spatio-temporal point patterns; 7. Development of methods for analysing spatially-referenced presence/absence data with applications in wildlife monitoring, disease epidemiology and farmland ecology; 8. Improvement of methods of marker-assisted selection; 9. Construction of improved identification key strategies by minimizing functions of expected number of tests and time taken for identification. 1997 The objectives for 1997 were entered in August 1997. Some are appropriate for 1998. In the area of design and analysis of experiments: 1. Development of algorithms for constructing factorial experiments when there are multiple error strata and constraints on aliasing of model terms; 2. Construction of pseudo- factors associated with these designs; 3. Construction of designs taking into account correlation between observations; 4. Extension of generalized linear models to take account of correlation; 5. Inprovement of existing estimation procedures, including using sampling assisted inference for correlated observations; 6. Extension of spectral techniques to spatio-temporal point patters; 7. Development of methods for analysing spatially-referenced presence/absence data with applications in wildlife monitoring, disease epidemiology and farmland ecology; 8. Construction of improved identification key strategies by minimizing functions of expected number of tests and time taken for identification. 9. Develop methods for assessing survival in large populations, taking account of genetic information and important covariates; 10. Develop methods to allow parsimonious models to be identified and fitted.

Summary

unavailable

Committee	Closed Committee - Engineering & Biological Systems (EBS)
Research Topics	X – not assigned to a current Research Topic
Research Priority	X – Research Priority information not available
Research Initiative	X - not in an Initiative
Funding Scheme	X – not Funded via a specific Funding Scheme

I accept the terms and conditions of use (opens in new window)

export PDF file

back to list new search