Scalable and Robust Bayesian Inference for Implicit Statistical Models. This project aims to develop the next generation of efficient methods for fitting complex simulation-based statistical models to data. Practitioners and scientists are interested in such implicit models to enable discoveries, produce accurate predictions and inform decisions under uncertainty. However, the associated computational cost has restricted researchers to implicit models that must have a small number of parameters ....Scalable and Robust Bayesian Inference for Implicit Statistical Models. This project aims to develop the next generation of efficient methods for fitting complex simulation-based statistical models to data. Practitioners and scientists are interested in such implicit models to enable discoveries, produce accurate predictions and inform decisions under uncertainty. However, the associated computational cost has restricted researchers to implicit models that must have a small number of parameters and be well specified, impeding scientific progress. This project will develop new computational methods and algorithms for implicit models that scale to high dimensions and are robust to misspecification. Benefits will arise from the more routine use of implicit models in epidemiology, biology, ecology and other fields.Read moreRead less
Improving productivity: theory and application to Australian hospitals. This project aims to improve existing methods for analysing productivity and efficiency of organisations. The new methods will be applied to Australian hospitals, to analyse their productivity and efficiency, identify the best-practices and their determinants and recommend improvements and necessary reforms. The high level of healthcare costs in Australia, about 5 percent of gross domestic product, as well as their rapid and ....Improving productivity: theory and application to Australian hospitals. This project aims to improve existing methods for analysing productivity and efficiency of organisations. The new methods will be applied to Australian hospitals, to analyse their productivity and efficiency, identify the best-practices and their determinants and recommend improvements and necessary reforms. The high level of healthcare costs in Australia, about 5 percent of gross domestic product, as well as their rapid and accelerating growth, imply that application of methods developed through this project may save billions of dollars and, more importantly, thousands of lives. An expected outcome of this project will be superior theoretical and practical methods for analysing productivity and efficiency of economic systems, to enhance understanding of the potential for improvements and of the necessary reforms.Read moreRead less
Statistical Methods for Next Generation Genome-Wide Association Studies. This project aims to develop cutting-edge statistical methods to analyse large genomic datasets and identify genetic variants associated with inter-individual differences in various human traits. Knowledge of trait-associated DNA variants is instrumental in understanding how natural selection has shaped human traits. By integrating genomic data from diverse and underrepresented populations, this project further expects to c ....Statistical Methods for Next Generation Genome-Wide Association Studies. This project aims to develop cutting-edge statistical methods to analyse large genomic datasets and identify genetic variants associated with inter-individual differences in various human traits. Knowledge of trait-associated DNA variants is instrumental in understanding how natural selection has shaped human traits. By integrating genomic data from diverse and underrepresented populations, this project further expects to contribute to the equitable use of genomic technologies in humans, regardless of geographical origins. Expected outcomes of this research include novel analysis methods and software tools, which should broadly and significantly benefit gene discovery in other species, including those of agricultural relevance.Read moreRead less
Solving the solvent problem in chemical modelling. This project aims to produce highly accurate, user-friendly chemical solvent models using interdisciplinary theoretical chemistry techniques. The benefits of these novel models are extremely broad since chemical modelling is more impactful than traditional laboratory based techniques in solving multi-faceted modern chemical problems. The proposed outcomes of the project are significant, as they will transform how applied research solves difficul ....Solving the solvent problem in chemical modelling. This project aims to produce highly accurate, user-friendly chemical solvent models using interdisciplinary theoretical chemistry techniques. The benefits of these novel models are extremely broad since chemical modelling is more impactful than traditional laboratory based techniques in solving multi-faceted modern chemical problems. The proposed outcomes of the project are significant, as they will transform how applied research solves difficult and expensive real world chemical problems by allowing researchers to reliably include solvents in their models. It will have economic benefits for the chemical, mining and materials sectors in Australia, which represent billion-dollar industries.Read moreRead less
An evolutionary landscape to better predict our future climate. Soil microbial communities are the most complicated and difficult to study on Earth, but their effects on our climate are profound. This project will examine the evolution of microorganisms and their viruses in soil using novel methods. It will uncover how the evolution of one microbial species influences the evolution of other community members. It will also apply a new model of evolution to the viruses that infect these microorgan ....An evolutionary landscape to better predict our future climate. Soil microbial communities are the most complicated and difficult to study on Earth, but their effects on our climate are profound. This project will examine the evolution of microorganisms and their viruses in soil using novel methods. It will uncover how the evolution of one microbial species influences the evolution of other community members. It will also apply a new model of evolution to the viruses that infect these microorganisms, constructing a viral ‘tree of life’. This improved fundamental understanding of soil communities will be used to study climate feedback from permafrost wetlands, a key and poorly constrained input of global climate models, improving predictions of our future climate.Read moreRead less
Representation theory of diagram algebras and logarithmic conformal field theory. Generalized models of polymers and percolation are notoriously difficult to handle mathematically, but can be described and solved using diagram algebras and logarithmic conformal field theory. Potential applications include polymer-like materials, filtering of drinking water, spatial spread of epidemics and bushfires, and tertiary recovery of oil.