Background and activities

This page is written for statisticians. The Norwegian page is written as popular science.

Research

I work in the statistics group, with spatial statistics. My main research interest is designing spatial random effects to incorporate valid scientific assumptions. I also focus on avoiding overfitting through sensible multi-level penalties/priors.

Spatial statistics: You have data distributed in space, which, after all the fixed effects are modelled, still have a spatial structure. 

 

Current research

How to make non-stationary spatial models where the non-stationarity can be understood and communicated? This research is based on the SPDE paper by Lindgren et. al. (2011)

Generic presentation - for use in talks

Haakon Bakka is a PhD student in spatial statistics at NTNU, where his main supervisor is Håvard Rue. Haakon's research is on fast spatial inference, where the spatial structure is designed to be consistent with scientific understanding of the underlying process. He uses stochastic partial differential equations to design the appropriate spatial correlation structure, in a computationally efficient manner. Shrinkage priors (for flexibility parameters) are also important for defining the underlying assumptions appropriately. He uses the integrated nested laplace approximations (through R-INLA) to make the models able to incorporate a diverse range of model components and likelihoods; including point patterns. His applications are focused on species distribution modeling, where the goal is to predict where the animals/plants are, and describe the habitats (the factors that drive the population).

Generic presentation - for use in INLA course descriptions

Haakon Bakka is a PhD student in spatial statistics at NTNU, where his main supervisor is Håvard Rue. His research is on fast spatial inference using R-INLA, where the spatial structure is designed to be consistent with scientific understanding of the underlying process.  His applications are focused on species distribution modeling, especially on habitats and abundance of aquatic animals. He has given INLA/SPDE courses in Pamplona and Zurich, with one underway in Valencia, with another two planned for Iceland and Canada.

 

Supervisors

Håvard Rue (http://www.math.ntnu.no/~hrue/)

Daniel Simpson (http://www.math.ntnu.no/~daniesi/)

Janine Illian (http://biology.st-andrews.ac.uk/contact/staffProfile.aspx?sunID=jbi)

Teaching

2013 Autumn: Lecturer Calculus 1 (TMA4100)

2014 Autumn: Teaching Assistant Statistics 1 (TMA 4240)

2015: Stand-in for several lecturers. Creating electronic learning materials.

2016: Giving INLA and SPDE courses (Pamplona, Zurich, Valencia)

Scientific, academic and artistic work

A selection of recent journal publications, artistic productions, books, including book and report excerpts. See all publications in the database

Report/dissertation

  • Bakka, Haakon Christopher; vanhatalo, jarno; Illian, Janine; Simpson, Daniel Peter; Rue, Håvard. (2016) Accounting for physical barriers in species distribution modeling with non-stationary spatial random effects. 2016.