Search

We consider a nonparametric Bayesian approach to estimate the diffusion coefficient of a stochastic differential equation given discrete time observations over a fixed time interval. As a prior on the diffusion coefficient, we employ a histogram-type prior with piecewise constant realisations on bins forming a partition of the time interval. Specifically, these constants are realizations of independent inverse Gamma distributed randoma variables. We justify our approach by deriving the rate at which the corresponding posterior distribution asymptotically concentrates around the data-generating diffusion coefficient. This posterior contraction rate turns out to be optimal for estimation of a Holder-continuous diffusion coefficient with smoothness parameter 0

Studies on vegetation and landscape changes resulting from water catchment in Dutch coastal dunes are briefly reviewed and discussed with special reference to Meijendel, an important catchment area near the city of The Hague. The water works mainly concern the extraction and artificial replenishment of ground water. Main ecological impacts involve lowering of the ground water table (after extraction) and (after replenishment) establishment of an unnatural ground water table and eutrophication. Main vegetation changes include drying out of dune wetlands and, after replenishment, increased nitrophilous herb cover associated with a decrease in plant species diversity and life form diversity. Management options largely aim at reducing the nutrient load of the ecosystem and regeneration of original hygrosere communities.