Bayesian Modeling of Presence-only Data

Abstract

This thesis develops models and methods for statistical analysis of presence-only data. Besides constructing new models, the emphasis is on the theoretical characteristics of new models and on Bayesian prediction. Monte Carlo Markov chains algorithms are developed for the new presence-only data models in order to be able to simulate the posterior distribution of the unknowns and the predictive distribution of variable of interest. The new methods are applied to simulated data. One application in ecologic science have been a driving force behind the work.