Stochastic Models in Ecology and Medicine - MAST8880

Overview

This module considers the development and application of stochastic models in two specific areas. The ecological part is focused on the analysis of data collected on wild animals. Particular attention will be given to estimating how long wild animals live, and also to estimating the sizes of mobile animal populations. The medical part also considers the estimation of survival, but in this case for human beings, with less data loss due to individuals leaving the study than is typical in ecological studies. In survival data it is often known only that individuals survived for a certain period of time, with exact survival time being unknown. This is called censoring and its implications will be discussed in detail. Outline Syllabus includes: Estimating abundance; estimating survival; using covariates; multi-state models; parameter redundancy; human survival data with censoring; the hazard and related functions; parametric and semiparametric survival models.

Details

Contact hours

30 lectures, 3 classes

Method of assessment

80% examination and 20% coursework

Indicative reading

Collett. D. (2003) Modelling Survival Data in Medical Research, Second Edition. Chapman & Hall/CRC, Boca Raton.
Williams, B.K., Nichols, J.D. and Conroy, M.J. (2001) Analysis and Management of Animal Populations. Academic Press, San Diego.?
Amstrup, S.C., McDonald, T.L. and Manly, B.F.J. (2005) Handbook of capture-recapture analysis. Princeton University Press. ?
McCrea, R.S. and Morgan, B.J.T. (2014) Analysis of capture-recapture data. Chapman and hall.CRC Press, Boca Raton.

See the library reading list for this module (Canterbury)

Learning outcomes

The intended subject specific learning outcomes. On successful completion of this module, students
- will have met a wide range of ecological and medical data sets, and understood how models may be derived for them;
- will have developed the skill of applying modern statistical techniques applicable to ecology and medicine;
- will have experience of modern statistical methods that make use of the power of modern computers, using RMARK and WinBUGS;
- will understand the use of stochastic modelling and the probabilistic concepts involved;

The intended generic learning outcomes. On successful completion of the module, students
- will have an appreciation of the originality required for problem solving, linked to research work taking place at the University of Kent;
- will have experience of the application of scientific computing to solve substantive real world problems;