Robust methods for heteroscedastic regression models for time series. What is the variability of the exchange rate of the Euro to the Australian dollar? Can the use of the electrocardiogram of a patient be improved as a diagnostic tool for heart disease? A well-known limitation of the existing statistical methods for answering these types of questions is that a small proportion of extreme observations have the potential to lead to results that are more in agreement with the outliers than with bu ....Robust methods for heteroscedastic regression models for time series. What is the variability of the exchange rate of the Euro to the Australian dollar? Can the use of the electrocardiogram of a patient be improved as a diagnostic tool for heart disease? A well-known limitation of the existing statistical methods for answering these types of questions is that a small proportion of extreme observations have the potential to lead to results that are more in agreement with the outliers than with bulk of the data. As a consequence, the statistical analyses may lead to wrong conclusions. This project aims to develop new methodologies to solve this problem for a large class of studies. Applications to stock market risk, exchange rate, and diagnosis of heart diseases will illustrate the new methods.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE200101070
Funder
Australian Research Council
Funding Amount
$376,496.00
Summary
Consequences of Model Misspecification in Approximate Bayesian Computation. In almost any empirical application, the model the analyst is working with constitutes a misspecified description of the true process that has generated the data. While the method of Approximate Bayesian computation (ABC) is now a staple in the toolkit of the applied modeller, the impact of misspecification in ABC is unknown. This project aims to undertake a rigorous study into the behaviour of ABC under model misspecifi ....Consequences of Model Misspecification in Approximate Bayesian Computation. In almost any empirical application, the model the analyst is working with constitutes a misspecified description of the true process that has generated the data. While the method of Approximate Bayesian computation (ABC) is now a staple in the toolkit of the applied modeller, the impact of misspecification in ABC is unknown. This project aims to undertake a rigorous study into the behaviour of ABC under model misspecification. Expected outcomes include new theoretical results for ABC under misspecification and new methods capable of detecting/mitigating model misspecification. This project will provide significant benefits in all spheres where reliable, robust statistical inference methods are required in order to make reliable decisions.
Read moreRead less
Predicting the value and use of urban land. This project aims to develop a comprehensive, robust and user-friendly set of modelling tools to predict land values more accurately. Accurate predictions of land values reduce state government revenue risks and improve resource management. The expected outcome of this project is the development of modelling tools which, can be used to study land use allocation, infrastructure delivery and government taxation revenue. This should provide significant be ....Predicting the value and use of urban land. This project aims to develop a comprehensive, robust and user-friendly set of modelling tools to predict land values more accurately. Accurate predictions of land values reduce state government revenue risks and improve resource management. The expected outcome of this project is the development of modelling tools which, can be used to study land use allocation, infrastructure delivery and government taxation revenue. This should provide significant benefits such as the development of new econometric theory, advanced computational methods and evidence-based guidelines for policymakers.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE230100029
Funder
Australian Research Council
Funding Amount
$345,197.00
Summary
Variational Inference for Intractable and Misspecified State Space Models. State space models (SSMs) are popularly used to model economic variables such as inflation and financial volatility. Variational inference is a technique that allows for fast implementation of SSMs, but whose properties are yet to be understood. This project aims to study the properties of variational inference for SSMs used in economics.
This research will develop new variational inference techniques to improve inferent ....Variational Inference for Intractable and Misspecified State Space Models. State space models (SSMs) are popularly used to model economic variables such as inflation and financial volatility. Variational inference is a technique that allows for fast implementation of SSMs, but whose properties are yet to be understood. This project aims to study the properties of variational inference for SSMs used in economics.
This research will develop new variational inference techniques to improve inferential and predictive accuracy from SSMs. An expected implication of this project is that it will expand the ability of economic institutions to employ larger SSMs, which will allow for more accurate models for economic variables. This will provide significant social benefits by leading to better informed economic policy.
Read moreRead less
Loss-based Bayesian Prediction. This project proposes a new paradigm for prediction. Using state-of-the-art computational methods, the project aims to produce accurate, fit for purpose, predictions which, by design, reduce the loss incurred when the prediction is inaccurate. Theoretical validation of the new predictive method, without reliance on knowledge of the correct statistical model, is an expected outcome, as is an extensive numerical assessment of its performance in empirical settings. T ....Loss-based Bayesian Prediction. This project proposes a new paradigm for prediction. Using state-of-the-art computational methods, the project aims to produce accurate, fit for purpose, predictions which, by design, reduce the loss incurred when the prediction is inaccurate. Theoretical validation of the new predictive method, without reliance on knowledge of the correct statistical model, is an expected outcome, as is an extensive numerical assessment of its performance in empirical settings. The new paradigm should produce significant benefits for all fields in which the consequences of predictive inaccuracy are severe. Problems that lead to substantial economic, financial or environmental loss if predictions are incorrect will be given particular attention.Read moreRead less
New methods for modelling complex trends in climate and energy time series. The project aims to contribute to Australian and international efforts on emission control by advancing the methods for quantifying the relationships between energy production, emission and climate, and assessing the real and financial risks associated with changing the ways in which economies produce and use energy. The project is interdisciplinary and expects to develop new knowledge in the areas of energy and climate ....New methods for modelling complex trends in climate and energy time series. The project aims to contribute to Australian and international efforts on emission control by advancing the methods for quantifying the relationships between energy production, emission and climate, and assessing the real and financial risks associated with changing the ways in which economies produce and use energy. The project is interdisciplinary and expects to develop new knowledge in the areas of energy and climate econometrics. The anticipated outcomes of this project are new methods for modelling variables with complex trends, and an innovative data-driven approach for learning from policy experiences of other countries. This should provide significant benefits by enabling evidence-based policy making in the era of climate change. Read moreRead less
Deep ocean thermodynamics and climate change. This project aims to obtain new insights into the thermodynamic and transport properties of mixtures containing water, particularly at high pressures, that impact directly on our understanding of climate change processes. The project will involve the use of a polarisable potential for water which has recently been demonstrated to yield predictions of high accuracy. It will be used to model saline water mixtures containing carbon dioxide, resulting in ....Deep ocean thermodynamics and climate change. This project aims to obtain new insights into the thermodynamic and transport properties of mixtures containing water, particularly at high pressures, that impact directly on our understanding of climate change processes. The project will involve the use of a polarisable potential for water which has recently been demonstrated to yield predictions of high accuracy. It will be used to model saline water mixtures containing carbon dioxide, resulting in valuable data for thermodynamic properties of the world's oceans. These data are of crucial importance for accurate climate change predictions and as such the project will have an important impact on understanding our changing environment.Read moreRead less
Prior sensitivity analysis for Bayesian Markov chain Monte Carlo output. This project aims to develop the first set of techniques to implement an automated output sensitivity analysis for Markov Chain Monte Carlo (MCMC) estimation methods. Computationally intense Bayesian MCMC provide a powerful alternative to classical methods for the estimation of economic models. An obstacle to their wider application is that researchers need to specify prior beliefs about model parameters that will affect t ....Prior sensitivity analysis for Bayesian Markov chain Monte Carlo output. This project aims to develop the first set of techniques to implement an automated output sensitivity analysis for Markov Chain Monte Carlo (MCMC) estimation methods. Computationally intense Bayesian MCMC provide a powerful alternative to classical methods for the estimation of economic models. An obstacle to their wider application is that researchers need to specify prior beliefs about model parameters that will affect the results. The expected outcomes will enable researchers to undertake a routine assessment of the sensitivity of the results to prior inputs.Read moreRead less
Statistical methods for quantifying variation in spatiotemporal areal data. This project aims to develop new statistical methods for extracting insights into spatial and temporal variation in areal data. These tools will extend the Australian Cancer Atlas which provides small area estimates for 20 cancers across Australia. The project is significant because it will allow government and other organisations to reap dividends from investment in collecting spatial information and it will enable mode ....Statistical methods for quantifying variation in spatiotemporal areal data. This project aims to develop new statistical methods for extracting insights into spatial and temporal variation in areal data. These tools will extend the Australian Cancer Atlas which provides small area estimates for 20 cancers across Australia. The project is significant because it will allow government and other organisations to reap dividends from investment in collecting spatial information and it will enable modelled small-area estimates to be released without compromising confidentiality. The expected outcomes include new statistical knowledge and new insights into cancer. The results will benefit the many disciplines, managers and policy makers that make decisions based on geographic data mapped over space and time. Read moreRead less
Molecular design of complex lubricants to reduce friction. We will investigate the molecular level design of friction modifiers for a new generation of industrial lubricants. The goal is to dramatically reduce friction between moving mechanical parts, hence increasing energy efficiency in machines and reducing global greenhouse gas emissions. We will design and test these new friction modifiers by a combination of theoretical and computational methods based in statistical mechanics and nonequili ....Molecular design of complex lubricants to reduce friction. We will investigate the molecular level design of friction modifiers for a new generation of industrial lubricants. The goal is to dramatically reduce friction between moving mechanical parts, hence increasing energy efficiency in machines and reducing global greenhouse gas emissions. We will design and test these new friction modifiers by a combination of theoretical and computational methods based in statistical mechanics and nonequilibrium molecular dynamics and directly compare results with experimental measurements. Our investigations will pave the way to develop new cost-effective friction modifiers without the need for traditional and costly trial and error laboratory based experimentation.Read moreRead less