Engineering and Information Sciences


Sandy Burden

Current Positions:



PhD in Statistics (University of Wollongong 2013) Title: Zone Issues in the Analysis of Small Area Health Data
Master of Statistics with Distinction (University of Wollongong 2003)
Bachelor of Engineering, Honours Class 1 and the University Medal in Mining (UNSW 1997)
Bachelor of Science, Honours Class 1 in Geology and Geophysics (University of Sydney 1994)

Research Interests:

Development of statistical methodologies for large and complex datasets, including spatial and spatio-temporal environmental datasets, population Census data and sample survey data. Statistical modelling, inference, and uncertainty quantification for spatial and spatio-temporal environmental processes. Statistical modelling of threshold exceedances. Statistical analysis of global remote sensing data and regional climate model predictions.

Professional Activities:

Council member and Young Statisticians representative for the NSW Branch of the Australian Statistical Society (SSA)
American Statistical Association, US (ASA), member
Royal Statistical Society, UK (RSS), member
American Geophysical Union (AGU), member


2016 Australian Research Council DECRA fellowship (2017 - 2019)
2004 APA Scholarship and CSIRO Top-up Scholarship
2002 UOW Summer Research Scholarship
1997 UNSW University Medal for outstanding academic achievement at the undergraduate level.
1996 Stan Sawyer Memorial Prize for the best performance in an honours thesis on a topic relating to coal mining by a student in the Bachelor of Engineering degree course in Mining Engineering.
1996 Shell Coal Undergraduate Scholarship
1995 Western Mining Perth Prize for the best overall performance by a student in third year of the Bachelor of Engineering degree course in Mining Engineering.
1994 Earth Resources Foundation Geo-Instruments Scholarship

Future Research Topics:

My current research aims to develop new statistical tools for improving prediction of environmental exceedances, such as atmospheric carbon dioxide sources and sinks. In particular, my DECRA research project seeks to develop tools using statistical inference based on a statistical model that combines existing predictions from multiple related scientific models to improve prediction accuracy and precision by reducing bias and uncertainty whilst accounting for model-based dependence. Using these results, environmental managers and decision-makers can more-reliably predict the effects of environmental change, and hence the impact of their decisions on people from communities around the globe, which is crucial for adaptive planning and a resilient society.

PhD Scholarship Opportunity:
A PhD Scholarship position is available in the School of Mathematics and Applied Statistics (SMAS) at the University of Wollongong, to work in the area of statistical modelling for spatial environmental processes. The UOW scholarship includes tuition fees and a stipend for three (3) years full-time, with a top-up scholarship available for outstanding candidates. The successful applicant will have the opportunity to work with both Australian and international collaborators, and funding is available for conference travel.

Applications are invited from domestic and international students who are able to commence their PhD studies at the University of Wollongong in 2017. Applicants should hold, or be close to completing an Honours 1 undergraduate degree or a Masters degree in Statistics or a closely related field with high GPA. The ideal candidate will have an interest in the development of statistical methodology, and the ability to develop skills in spatial statistical modelling of extremes and exceedances. The candidate will be self-motivated, with strong research potential, good programming skills, and good oral and written communication skills.

The project is motivated by the compelling need to predict the effect of changing greenhouse gas concentrations on Earth's atmosphere for political, social and economic decision making. It aims to develop statistical tools to improve prediction of environmental exceedances (locations where the environmental process of interest exceeds a given threshold). The successful applicant will investigate innovative methods for predicting exceedances for large, non-Gaussian spatial processes, based on output from multiple related scientific models. Computationally efficient modelling techniques will be required, that effectively model the tails of the distribution when there is spatial variation in uncertainty.

Please contact Dr Sandy Burden (sburden [at] for further information, or to apply for this position. Applications are due by 1st March 2017.