The fortnightly BRAG meeting will be held this Thursday 08/09 at 1 pm via Zoom/GP-Y801. This week we will have presentations by @Owen Forbes and @Tace Stewart.
Zoom Link: https://qut.zoom.us/j/85315873893?pwd=bWlWci9lM2Z3RmFCdjc5bmppWG1qUT09
Password: brag@QUT (if prompted)
Owen’s Talk
Title: clusterBMA: Combine insights from multiple clustering algorithms with Bayesian model averaging
Abstract: Clustering is one of the most common tasks for applied statisticians across a wide variety of industry, government and research settings. When an analyst reports results from one ‘best’ model out of several candidate clustering models, this ignores the uncertainty that arises from model selection, and results in inferences that are sensitive to the particular model and parameters chosen.
In this work we introduce clusterBMA, extending Bayesian Model Averaging (BMA) methodology to combine inference across multiple algorithms for unsupervised clustering of a given dataset, using a combination of clustering internal validation criteria to weight results from each model. BMA offers some attractive benefits over other existing approaches. Benefits include intuitive probabilistic interpretation of an overall cluster structure integrated across multiple sets of clustering results, flexibility to accommodate various input algorithms, and quantification of model-based uncertainty. These features enable improved communication of uncertainty and variability across models for clustering applications, allowing clients to gain clearer understanding of the insights offered by different clustering methods and uncertainty in cluster structure across models.
We present results from a simulation study to explore the utility of this technique for identifying robust integrated clusters with model-based uncertainty, under varying conditions of separation between simulated clusters. We then implement this method in a substantive real world case study, clustering young people based on electrical brain activity and relating these clusters to measures of mental health and cognitive function. Our method offers extra insight compared to clustering results from individual algorithms, particularly regarding consistency or ambiguity in cluster allocations between multiple clustering algorithms. This case study demonstrates the utility of clusterBMA in health applications where model-based uncertainty is relevant for communication of risk to clinicians and patients.
The method is implemented in the R package “clusterBMA” (https://github.com/of2/clusterBMA), and I will show a demo during my talk.
Tace’s Talk
Title: Conservation planning in the presence of cumulative disasters
Abstract: Coral cover of reefs has declined globally over the past 30 years. Some of the pressures on coral cover include cyclones, bleaching, and crown-of-thorns starfish. Planning conservation with these events in mind is necessary to ensure optimal species preservation continues during and after disturbances occur.
Our research investigates the likelihood and impact of disturbances compounding in time or space, as they can result in disasters. The aims of this study are to analyse the history of compounding disturbances in the Great Barrier Reef, including its impact on coral cover and the expected recovery time given the combined disturbances. This study also proposes a marine protection plan that considers the impact of compounding disturbances, and increases coral resilience against such events.