Casual Inference Methods for Promoting Behavioural and Implementation Change in Health: Insights from Observational Studies and Harnessing Population Heterogeneity in Experiments

Applied health and social research often seeks to estimate the causal effects of risk factors or interventions from studies or experiments, aiming to guide strategy, management, and funding decisions through analyses and evaluations. These efforts address causal questions like the potential benefits or harms of new policies or interventions. However, the causal interpretation and unbiased estimation of these effects from study data are not always straightforward. Furthermore, even if the effect of an intervention is causal (internal validity) there is uncertainty in regards to intervention effectivenss, appropriateness, feasibility, acceptability, cost, and sustainability (external validity) in different populations. The workshop will: - Improve delegates’ understanding of the field of causal modelling and evaluation, including essential frameworks and theories - Enable delegates to choose an appropriate design framework for evaluation of a policy/intervention - Enable delegates to identify and accurately describe hybrid designs which incorporate elements of clinical effectiveness and implementation. - Support delegates to apply knowledge gained about causal modelling and evaluation which could employ in a wide spectrum of industry and research roles - Provide an overview of methods that are easily accessible to the applied researcher.