PhD scholarship

University of Wollongong

Applications are invited for a full-time PhD scholarship at the University of Wollongong within the Centre for Statistical and Survey Methodology. The scholarship is funded by an ARC Discovery Project grant, Statistical Inference for Probability-Linked Longitudinal Data, recently awarded to Professor Ray Chambers.

Over the last 25 years, advances in information technology have led to the creation of databases containing vast amounts of information relevant to research in health, epidemiology, economics, demography, sociology and many other scientific areas. However, much of this information is inaccessible unless these databases are linked, allowing researchers to investigate relationships between variables on different databases. As a consequence, there has been a considerable investment in the development of record linkage methods which can be used to merge distinct data sources into a single dataset in the absence of unique identifiers. This is typically carried out via record matching using a probability-based algorithm.

Although statistical methods for efficient matching are now well established, there has been comparatively little research carried out on the impact of linkage errors on analysis of linked data. Linkage errors are the errors caused by incorrectly linking distinct population units as well as the errors caused by not linking the same population units in the datasets that are linked. Linkage errors are a particular type of measurement error, and can lead to biased inference unless appropriate steps are taken to control and/or adjust for this bias. This project will develop methods for efficient maximum likelihood inference for generalized linear models and generalized linear mixed models using linked data, thereby significantly extending the range of analyses that can be validly carried out with these data. In particular, models for probability linkage methods in common use will be combined with these widely used data models in order to allow information about the linkage error process to be used in efficient inference. It is anticipated that the student involved in this project will work with the Australian Bureau of Statistics and other agencies to develop user-friendly approximate methods that these organizations can provide to researchers who wish to carry out valid statistical inference using their linked data resources.

The successful applicant will work in a vibrant and growing research centre, the Centre for Statistical and Survey Methodology, at the University of Wollongong. The Centre comprises 10 academic statisticians, including four professors, and 15 PhD students. The project will involve some travel, including visits to Canberra, Sydney and Perth to meet with agencies interested in applying the results of the research. There may also be opportunities for overseas travel since the Centre has strong connections with the University of Manchester and the University of Southampton in the UK.

The scholarship includes a tax-free stipend that is currently worth a minimum of $25,627 per year for three years. Depending on the research experience and background of the successful applicant, there may be opportunities to supplement the stipend with tutoring or other casual work. Additional funding is available for computing equipment and travel.

This scholarship is only open only to Australian citizens, Australian permanent residents and New Zealand citizens. Applicants should have an Honours 1 or 2(1) degree in Statistics, or an equivalent qualification, strong research potential and be able to commence by the end of June 2008. Applications, including a curriculum vitae, academic transcript, proof of citizenship or permanent residency and contact details of two or more referees should be sent to Prof Ray Chambers, Centre for Statistical and Survey Methodology, School of Mathematics and Applied Statistics, University of Wollongong, NSW 2522. Closing date: Friday April 18, 2008.

Enquiries about the project or the Centre are welcome. For more information, please contact Professor Ray Chambers, ph (61) 2 42213809, email ray@uow.edu.au.