Background and activities
My main interests lie in spatio-temporal statistics and computational statistics. In particular, the use of stochastic partial differential equation (SPDE) models for fast computations with spatio-temporal processes. I am interested in applications in a wide range of scientific fields from epidemiology and demography to physical sciences.
From 2020 we are starting the project MASCOT (Maritime Autonomous Sampling and Control). This is an inter-disciplinary project that aims to develop and design observational strategies in spatio-temporal domains, enabling autonomous platforms to decide on a strategy of where and when to make measurements to increase our knowledge of dynamic environments like the upper water-column.
I'm invoved in the development of the R-package SUMMER (Spatio-Temporal Under-Five Mortality Methods for Estimation), where the target is to take advantage of complex, but easy-to-use and computationally efficient methods for subnational mapping of under-five mortality in low- and medium-income countries. This work is lead by Jon Wakefield at the University of Washington, Seattle, USA.
I'm also interested in methodological development in Bayesian statistics, and I'm taking part in the project "Penalized Complexity-priors: A new tool to define default priors and robustify Bayesian models" (NFR), which is lead by Andrea Riebler at IMF, NTNU. This project aims to create a framework for specifying intuitive and robust joint priors for several variance parameters in a latent Gaussian model. The end goal is an R package that allows the developed framework to be easily used by all scientists fitting latent Gaussian models.
See here for more details.
Scientific, academic and artistic work
Displaying a selection of activities. See all publications in the database
- (2019) Intuitive Joint Priors for Variance Parameters. Bayesian Analysis.
- (2019) Constructing Priors that Penalize the Complexity of Gaussian Random Fields. Journal of the American Statistical Association. vol. 114 (525).
- (2019) Estimating under-five mortality in space and time in a developing world context. Statistical Methods in Medical Research. vol. 28 (9).
- (2018) Spatial modelling with R-INLA: A review. Wiley Interdisciplinary Reviews: Computational Statistics. vol. 10:e1443 (6).
- (2018) Environmental mapping using Bayesian spatial modelling (INLA/SPDE): A reply to Huang et al. (2017). Science of the Total Environment. vol. 624.
- (2017) Predicting soil properties in the Canadian boreal forest with limited data: Comparison of spatial and non-spatial statistical approaches. Geoderma. vol. 306.
- (2016) Assessing comorbidity and correlates of wasting and stunting among children in Somalia using cross-sectional household surveys: 2007 to 2010. BMJ Open. vol. 6:e009854 (3).
- (2016) Landscape relatedness: detecting contemporary fine-scale spatial structure in wild populations. Landscape Ecology. vol. 32 (1).