Dr Murthy Mittinty
Menzies Health Institute Queensland Workshop
Mediation Analysis: A Counterfactual Approach with Dr Murthy Mittinty
The aim of this workshop is to provide an outline of recent developments in mediation analysis, that is, the analyses used to assess the relative magnitude of different pathways and mechanisms through which an exposure may affect an outcome.
The purpose of the workshop is to provide:
(i) Conceptual understanding and interpretability of the results;
The workshop will cover traditional approaches to mediation such as product and difference methods and introduce the latest developments such as counterfactual approach. Importance will be given to the confounding assumptions required for a casual interpretation of direct and indirect effect estimates. Methods from the casual inference literature to conduct meditation in the presence of exposure mediator interactions, binary outcomes, binary mediators, and case-control study designs will be demonstrated. Sensitivity analysis techniques for unmeasured confounding and measurement error will be introduced. Discussion will focus on extending single mediation analysis to multiple mediators.
(ii) Using epidemiological data practical applications of the above methods will be demonstrated. Analysis will be demonstrated using commonly used software such as STATA.
(iii) Emphasis will also be given on report and communication of the estimates from the above methods.
Murthy N Mittinty is a senior lecturer at the School of Public Health, The University of Adelaide. He is an accrediated Statistician of the Statistical Society of Australian. He has his training in mathematical Statistics from India and New Zealand. Murthy's research interests are in application of statistical methods to problems concerning public health, design and analysis of observational data, imputation of missing and causal inference. Apart from statistical research Murthy has a keen interest in philosophy of science.
Please RSVP here
This is for catering purposes.
RSVP by email email@example.com, or by phone (07) 5678 8811 , or via https://docs.google.com/forms/d/e/1FAIpQLSetds_YXlZlZT2PSfhZIMq9Q0kraMoHD0cZywL4cW5Ug-vnKQ/viewform