Causal Inference

Policy-makers requires studies that provide accurate, precise cost-effectiveness estimates to inform clinical guidelines, and for deciding which public health interventions and health care technologies to provide. Economic evaluations may provide misleading evidence because they fail to address issues such as

low external validity

confounding

non-compliance

missing data

clustering

Our research programme draws on insights from the causal inference literature in developing methods that help address these problems. Causal inference is an expanding multidisciplinary field with contributions from statistics, computer science, and the biomedical and social sciences. Drawing on these developments, we propose new approaches for providing accurate cost-effectiveness estimates in target populations of high policy-relevance.

Key people: Richard Grieve, Manuel Gomes, Noemi Kreif, Alexina Mason

Comments are closed.