Increasing awareness about the presence and ecological ramifications of toxic, persistent and bioaccumulative contaminants within the Great Lakes system spurred the implementation of numerous bans and emissions restrictions over the past few decades. Due to their high trophic status in food webs and the critical link they serve with human consumers, fish species have historically been monitored to assess the relative success of such remedial efforts within the region and to simultaneously ascertain the current risks posed to local humans. Using Bayesian dynamic linear modelling, this project first aimed to evaluate temporal trends of various organochlorine contaminants within Lake Erie fish communities, the results of which generally indicated decreasing trends through time. The second half of this study used a similar Bayesian approach to propose a framework for updating fish consumption advisories, with specific attention paid to the acknowledgment of uncertainty and natural variability when producing such consumption guidelines.

Increasing awareness about the presence and ecological ramifications of toxic, persistent and bioaccumulative contaminants within the Great Lakes system spurred the implementation of numerous bans and emissions restrictions over the past few decades. Due to their high trophic status in food webs and the critical link they serve with human consumers, fish species have historically been monitored to assess the relative success of such remedial efforts within the region and to simultaneously ascertain the current risks posed to local humans. Using Bayesian dynamic linear modelling, this project first aimed to evaluate temporal trends of various organochlorine contaminants within Lake Erie fish communities, the results of which generally indicated decreasing trends through time. The second half of this study used a similar Bayesian approach to propose a framework for updating fish consumption advisories, with specific attention paid to the acknowledgment of uncertainty and natural variability when producing such consumption guidelines.

To avoid irreversible damage to the climate system and biosphere, the majority of the world’s countries must reduce rates of resource throughput. However, the socio-economic conditions for satisfying basic human needs at low resource use have received scant empirical attention. I apply cross-country panel analysis and dynamic linear modelling to explore how different dimensions of inequality affect countries’ abilities to deliver a good life for all at sustainable levels of carbon consumption. My results suggest that inequalities reduce socio-ecological performance, with income inequality reducing the proportion of carbon channelled into meeting basic needs and wealth inequality increasing the carbon-intensity of expenditure. Overall, this study highlights the importance of reducing inequalities in a resource-constrained world. Social media summary. Income inequality raises the carbon cost of meeting basic human needs at the national and global scales.

This thesis addresses spatial interpolation and temporal prediction using air pollution data by several space-time modelling approaches. Firstly, we implement the dynamic linear modelling (DLM) approach in spatial interpolation and find various potential problems with that approach. We develop software to implement our approach. Secondly, we implement a Bayesian spatial prediction (BSP) approach to model spatio-temporal ground-level ozone fields and compare the accuracy of that approach with that of the DLM. Thirdly, we develop a Bayesian version empirical orthogonal function (EOF) method to incorporate the uncertainties due to temporally varying spatial process, and the spatial variations at broad- and fine- scale. Finally, we extend the BSP into the DLM framework to develop a unified Bayesian spatio-temporal model for univariate and multivariate responses. The result generalizes a number of current approaches in this field.

This thesis addresses spatial interpolation and temporal prediction using air pollution data by several space-time modelling approaches. Firstly, we implement the dynamic linear modelling (DLM) approach in spatial interpolation and find various potential problems with that approach. We develop software to implement our approach. Secondly, we implement a Bayesian spatial prediction (BSP) approach to model spatio-temporal ground-level ozone fields and compare the accuracy of that approach with that of the DLM. Thirdly, we develop a Bayesian version empirical orthogonal function (EOF) method to incorporate the uncertainties due to temporally varying spatial process, and the spatial variations at broad- and fine- scale. Finally, we extend the BSP into the DLM framework to develop a unified Bayesian spatio-temporal model for univariate and multivariate responses. The result generalizes a number of current approaches in this field.

This thesis addresses spatial interpolation and temporal prediction using air pollution data by several space-time modelling approaches. Firstly, we implement the dynamic linear modelling (DLM) approach in spatial interpolation and find various potential problems with that approach. We develop software to implement our approach. Secondly, we implement a Bayesian spatial prediction (BSP) approach to model spatio-temporal ground-level ozone fields and compare the accuracy of that approach with that of the DLM. Thirdly, we develop a Bayesian version empirical orthogonal function (EOF) method to incorporate the uncertainties due to temporally varying spatial process, and the spatial variations at broad- and fine- scale. Finally, we extend the BSP into the DLM framework to develop a unified Bayesian spatio-temporal model for univariate and multivariate responses. The result generalizes a number of current approaches in this field. / Science, Faculty of / Statistics, Department of / Graduate