We use cookies to ensure that we give you the best experience on our website. You can change your cookie settings at any time. Otherwise, we'll assume you're OK to continue.

Department of Mathematical Sciences

Seminar Archives

On this page you can find information about seminars in this and previous academic years, where available on the database.

Statistics Seminars: The Analysis of Ecological Data through the Eyes (and Computer) of a Bayesian

Presented by Ruth King (University of St Andrews),

9 December 2005 14:00 in CM107

"Ecological data can be collected in a number of ways, generally dependent on the particular biological questions of interest. We focus on capture-recapture data often collected to obtain estimates of demographic parameters of interest, and consider in detail data relating to a population of Soay sheep. Several issues arise within this particular dataset that need to be addressed in the analysis of the data. Additional covariate information is collected, which we wish to incorporate into the analysis, however, some of these covariate values are missing (i.e. not recorded). Further, not only is parameter estimation of interest, but also the identification of the underlying model, i.e. the covariates that influence the survival rates of the population. This can be very important in understanding the underlying dynamics of the population, as well as making predictive inference. In order to fit the models to the data and obtain insight into the behaviour of the population, we use a Bayesian approach; a paradigm which is becoming increasingly widespread within Ecology. In particular, we are able to quantitatively discriminate between competing models via posterior model probabilities, and obtain posterior model-averaged estimates of interest. These are obtained via the reversible jump MCMC algorithm. We will discuss the results obtained, and their corresponding biological interpretation, including the impact of breeding and condition on the survival of the sheep. "

Contact for more information