Canberra Branch meetings
Our final meeting of the year will be the Knibbs Lecture on Tuesday 10 December, presented by Prof. James Carpenter. James is an invited speaker at the International Biometric Society Australasian Region conference the previous week in Adelaide. So we invited him to come to Canberra after that conference, before returning to the UK. After the talk there will be a dinner at Bamiyan Restaurant, Braddon.
Date: Tuesday 10 December 2019
5.15pm Refreshments, Allan Barton Forum, Level 2, Room 248, College of Business and Economics, ANU (Map).
6.00pm Presentation in Allan Barton Forum.
6.55pm Response and general discussion
7.30pm After the talk, there will be dinner at Bamiyan Restaurant, 62/10 Lonsdale Street Braddon (Restaurant).
Please RSVP Warren Muller (reply to this email directly) by 5 p.m. Friday 6 December if you would like to attend the dinner. Please note we will be planning to order a banquet. Cost will be $40. Anyone with special dietary requirements should let me know when responding.
Discussant: Dr Alice Richardson, ANU
Topic: Missing data: a statistical framework for practice
Missing data are ubiquitous in social and medical research, yet there is still uncertainty over when restricting to the complete records is likely to be acceptable, when more complex methods (e.g. multiple imputation, the EM algorithm and Bayesian methods) should be used, how they relate to each other, and the role of sensitivity analysis. In this talk I propose a framework for thinking about the issues raised by missing data; briefly review and relate current methodologies, and describe practical approaches for applied statisticians, in particular in the field of multiple imputation and sensitivity analysis. The ideas are illustrated with a cohort study, a multi-centre case control study and a randomised clinical trial.
James Carpenter is professor of medical statistics at the London School of Hygiene & Tropical Medicine and Programme Leader in Methodology at the MRC Clinical Trials unit at University College London. He has broad interests in methodology for clinical trials and observational studies, and a long-standing research interest in the analysis of partially observed data. He has led many missing data workshops, and in 2013 he co-authored Multiple imputation and its application (Wiley) with Mike Kenward.