We’ve just revised and re-arxived our manuscript on point processes for the analysis of eye movement data (joint work with Hans Trukenbrod & Ralf Engbert of the University of Potsdam, Felix Wichmann of the University of Tübingen).

The main idea is that often one is interested mostly in where people have looked and why. Fixation locations at are just points in space, and so you can analyse that sort of data with point processes. The reason you’d want to do that is that point processes give interesting ways of characterising the statistical patterns of points in space. The thing we focus on is predicting what people look at based on image content, but that’s only one of the many things you can do in that framework.
example_dep_initial_fix
Of potential interest to eye movement researchers and people who like statistical models of stuff.

New in this version:

  • What to do when your data aren’t stationary (when there are temporal dependencies).
  • Statistical properties of other methods studied under point process assumptions.
  • Much expanded literature review.
  • Following reviewer feedback & academic tradition, language revised to be bland, stilted and repetitive.

Get the paper here.