Abstract: Most governments, companies and researchers are now aware of the need for data-focused decision-making. Often, however, these data are held by multiple data custodians who are unwilling or unable to share for reasons of privacy, commercial confidentiality, security or management. An appealing option is to create alternative data assets that can be made open with mild caveats. Moreover, although this might address the issue of data access, organisations face a second challenge of making sense of overwhelming amounts of data, particularly if the focus is on local decision-making.
In this presentation, we consider a number of remedies to these challenges, based on Bayesian statistical models. These include robust, privacy-preserving spatial models, probabilistic insights and novel visualisations. We discuss these in the context of the Australian Cancer Atlas, the first interactive digital atlas of small-area estimates of incidence and survival for around 20 cancers. The first release of the ACA focused on geographic inequity. The current update is focusing on spatio-temporal extensions with increased decision support. We will also touch on extensions that will support our work, including federated learning for hierarchical spatial models.
Bio: Kerrie Mengersen is a Distinguished Professor of Statistics and Director of the Centre for Data Science at QUT. Her career in statistical consulting and academic research has taken her across three states of Australia, the USA and France. Kerrie is a Fellow of the Australian Academy of Science, the Australian Academy of Social Sciences, and the Queensland Academy of the Arts and Sciences. Her overall ambition is to 'use data better', particularly in the fields of health, environment and industry. To this end, she has led over 30 major projects such as the current Long-term Benefits and Impacts Study with Queens Wharf Brisbane, the online interactive Australian Cancer Atlas and the Virtual Reef Diver program.