Causal inference in cancer epidemiology
The Norwegian cohort studies and health registries represent a unique treasure, which needs to be more extensively exploited with efficient modern analytical tools. We will in collaboration with the research group Epidemiological Studies of Lifestyle and Chronic Diseases use techniques from modern causal inference to study the complex associations between UV exposure and melanoma. Is high UV exposure at young age more harmful than high exposure later in life? What proportion of the risk due to high UV exposure at young age is actually caused by continued high UV exposure?
Analyzing clinical registries: The need for causal inference
Funded by the Norwegian Cancer Society.
EU-project: Novel Statistical Methodology for Diagnostic/Prognostic and Therapeutic Studies and Systematic Reviews.
New analytic methods in epidemiology
Norwegian Research Council project. The aim is to develope new methods for causal inference in data, with special emphasis on time-dependent confounding and time-dependent mediation.
Analyzing sickness absence, disability, and withdrawal from the labour market: The need for causal inference.
Funded by the Norwegian Research Council.
The impact of individual heterogeneity (frailty) in cancer
Norwegian Cancer Association project. The aim is to study individual susceptibility with respect to cancer risk. We are using individual as well as family data in cooperation with the Cancer Registry of Norway.
Estimating incidence of cancer and HIV in Malawi
Statistical modeling for infectious disease
Norwegian Research Council project. Emphasis on cost aspects related to influenza epidemics (the project is also described by Birgitte Freiesleben de Blasio).