G. GILIOLI, S. PASQUALI, F. RUGGERI
Bayesian inference for functional response in a stochastic predator-prey system
Bulletin of Mathematical Biology 70, 358-381 (2008)
We present a Bayesian method for functional response parameter
estimation starting from time series of field data on predator-prey
dynamics.
Population dynamics is described by a system of stochastic differential
equations in which behavioural stochasticities are represented by noise
terms affecting each population as well as their interaction.
We focus on the estimation of a behavioural parameter appearing in the
functional response of predator to prey abundance when a small
number of observations is available. To deal with small sample sizes,
latent data are introduced between each pair of field observations and
are considered as missing data.
The method is applied to both simulated and observational data. The
results obtained using different numbers of latent data are compared
with those achieved following a frequentist approach. As a case study
we consider an acarine predator-prey system relevant to biological
control problems.
