You are warmly invited to participate in SSA Vic’s 2018 AGM, to be followed by “Data and Decision Making”, a seminar presented by Professor Howard Bondell. The AGM is a great opportunity to have your say in what SSA Vic gets up to this year: what can the branch do for you? Come along with your suggestions! Proxy nomination forms (see below) are available for members unable to attend the AGM in person. AGM and seminar details below.
5:45pm – AGM, Staff Tea Room, Peter Hall Building (https://maps.unimelb.edu.au/parkville/building/160), University of Melbourne
6:30pm – Seminar, Carillo Gantner Lecture Theatre, Sidney Meyer Asia Centre University of Melbourne (https://goo.gl/maps/1CSfsMPrWE22)
7:45pm – Dinner at Café Italia in Carlton
The Annual General Meeting is open to all members of the Victorian Branch of the Statistical Society of Australia. Meeting documents: Minutes of last meeting, Agenda, Proxy nomination forms, nomination for SSA Vic council, President’s and Treasurer’s Reports.
Seminar: Data and Decision-Making: Informative Missingness, Recommender Systems, and Personalised Medicine
Howard Bondell, Professor of Statistics and Data Science, University of Melbourne
In this talk, we will discuss two topics associated with the use of data for decision-making. The first part of the talk investigates informative missingness in the framework of recommender systems. In this setting, we envision a potential rating for every object-user pair. The goal of a recommender system is to predict the unobserved ratings and then recommend an object that the user is likely to rate highly. A typically overlooked piece is that the combinations are not missing at random. For example, in movie ratings, a relationship between the user ratings and their viewing history is expected, as human nature dictates the user would seek out movies that they anticipate enjoying. We model this informative missingness, and place the recommender system in a shared-variable regression framework which can aid in prediction quality. The second part of the talk deals with personalised medicine, which relies on the ability to prescribe patient-specific treatments. In this context, it is crucial to identify the variables that impact the optimal treatment decision. Typical variable selection techniques target on selecting variables that are important for prediction, which are not necessarily those that are important for treatment assignment. We propose a Gaussian process model in a backward elimination framework to identify the important variables in treatment decision making.