Master’s project for MS in statistics at OSU
Major Professor: James Molyneux
Committee Members: Lisa Madsen & Charlotte Wickham
Events such as earthquake epicenters, crime patterns, forest wildfires, financial transactions, etc. often exhibit triggering and clustering behavior. The ability to capture events with such behavior gives Hawkes or self-exciting point processes (SEPP) the potential to become a powerful predictive tool for a wide variety of applications. In this project, we give brief introductions, review definitions, discuss properties and applications of selected spatial and temporal point processes leading up to spatio-temporal SEPP, and simulate some of the processes in 1D and 2D in hope that interested readers have the background knowledge to comprehend existing SEPP literature as well as explore the field further.
Main report for this project can be found here and presentation slides can be found here.
Other reports are in the analysis folder:
01_proc_HPP.Rmd simulates HPP.
03_proc_Hawkes.Rmd simulates Hawkes process.
04_proc_using_spatstat.Rmd simulates HPP, NPP, Cox and cluster processes in 2D using the spatstat package of R.
Lin_Appendix.pdf contains the algorithm in particular the thinning algorithm and spatstat package of R used for simulating some of the processes in 1D or 2D.
Lin_Presentation.Rmd contains codes that produce slides for the presentation.