Min/Max Autocorrelation Factors in Time Series Studies of the Adverse Health Effects of Ozone. The annual health costs associated with exposure to air pollution in Australia have been estimated at between $3 and 5.3 billion. Given these costs, it is vital to conduct research that ensures public health officials and policy makers stay fully informed of Australia’s air pollution problem. The project proposes to address this need by developing methodology to detect trends in air pollution concentra ....Min/Max Autocorrelation Factors in Time Series Studies of the Adverse Health Effects of Ozone. The annual health costs associated with exposure to air pollution in Australia have been estimated at between $3 and 5.3 billion. Given these costs, it is vital to conduct research that ensures public health officials and policy makers stay fully informed of Australia’s air pollution problem. The project proposes to address this need by developing methodology to detect trends in air pollution concentrations and reduce measurement error in recorded air pollution concentrations. This will enable relevant authorities to produce more accurate estimates of air pollution health costs and implement more appropriate pollution regulations and health warnings.Read moreRead less
Statistical Inference for Probability-Linked Longitudinal Data. The Strategic Roadmap for the Australian Government's National Collaborative Research Infrastructure Strategy states that analysis of linked data, and particularly linked longitudinal data, has the potential to revolutionise Australian public health research. Similar benefits should flow from analysis of linked datasets in other areas, e.g. the Statistical Longitudinal Census Dataset that the Australian Bureau of Statistics intends ....Statistical Inference for Probability-Linked Longitudinal Data. The Strategic Roadmap for the Australian Government's National Collaborative Research Infrastructure Strategy states that analysis of linked data, and particularly linked longitudinal data, has the potential to revolutionise Australian public health research. Similar benefits should flow from analysis of linked datasets in other areas, e.g. the Statistical Longitudinal Census Dataset that the Australian Bureau of Statistics intends to create by linking individual records across censuses. These benefits will be maximised by controlling the impact of linkage error when analysing these datasets. This proposal will develop the statistical theory and related methodology to solve this problem in a statistically efficient manner.Read moreRead less
Air pollution: do modern statistical model selection techniques make the silent killer speak too loud? Air pollution is estimated to cause 2400 deaths annually in Australia with an associated cost to the community of $17.2 billion. The outcomes of this project will enable an improved understanding of the association between air pollution and mortality in Australia, thereby allowing government, public health authorities, and regulatory agencies to implement better air pollution standards and pro ....Air pollution: do modern statistical model selection techniques make the silent killer speak too loud? Air pollution is estimated to cause 2400 deaths annually in Australia with an associated cost to the community of $17.2 billion. The outcomes of this project will enable an improved understanding of the association between air pollution and mortality in Australia, thereby allowing government, public health authorities, and regulatory agencies to implement better air pollution standards and provide more informed advice to the public on the necessity of avoiding exposure to air pollutants. These two outcomes are particularly important given Australia's ageing population and the fact that the elderly are among those most susceptible to harm from air pollution exposure.Read moreRead less
Theory and applications of Bayesian and likelihood analyses for finite mixture, random effect and multinomial models. The expected outcomes of the project are: to establish the scientific
value of modern Bayesian methods for statistical inference in a wider
range of applications than previously available, to contribute to the greater unification of the current theories of statistical inference which are to some extent in conflict, and to provide a set of Bayesian analytic tools implemented in ....Theory and applications of Bayesian and likelihood analyses for finite mixture, random effect and multinomial models. The expected outcomes of the project are: to establish the scientific
value of modern Bayesian methods for statistical inference in a wider
range of applications than previously available, to contribute to the greater unification of the current theories of statistical inference which are to some extent in conflict, and to provide a set of Bayesian analytic tools implemented in widely available, free and open-source statistical software.
Read moreRead less