Parameter and uncertainty estimation for process-oriented population and distribution models: data, statistics and the niche

G.Marion, G.J.McInerny, J.Pagel, S.Catterall, A.R.Cook, F.Hartig and R.B.O’Hara

Journal of Biogeography, 2012, Volume 39, Issue 12, pages 2225–2239

DOI: 10.1111/j.1365-2699.2012.02772.x

Used by the Quanticol project

This is a review paper which gives an introduction to parameter estimation in the Bayesian framework based on MCMC. Thus there are no original results but a clear explanation of existing techniques illustrated by three case studies of increasing complexity, both in terms of the models and the availability of data, starting from a deterministic model which is assumed to be in equilibrium and for which there is spatial data only for one time point, to a stochastic model with two time points, to a more complete time series and more detailed mechanistic model.