Many natural systems such as wildfires, disease occurrences, plant and cellular systems, and animal colonies are observed as point patterns in time, space or space and time. For data of this type, statistical point process models are commonly used to describe the data generating process. Point process methodology is thus applied by scientists in various fields to enhance their understanding of the underlying scientific phenomena behind their subject matter. However, the use of these models can be hindered by their complicated nature and an improved understanding of the data generating process requires, in particular, a coherent framework for model comparison and model selection.

 

In this project, we will develop new methodology for validating and selecting the most appropriate model for a given data set using Bayesian and decision theoretic principles. This will make it easier for non-experts to apply point process models and thus advance their use for investigating complex scientific hypotheses.

 

This four year research project runs from January 1, 2015 to December 31, 2018. It is funded by the Research Council of Norway under the FRIPRO program for young research talent.