Statistics
Postgraduate Research

Statistics supports a lively and growing community of post-graduate research students who make up a key part of our research activities.

Scholarships are available for Research Higher Degree students, from time to time including ones specifically for Statistics students. Please see the Research Scholarships site.

Students interested in undertaking RHD contact staff in their area of research interest or the Statistics RHD Coordinator.

Current and recent research projects include:

Bivariate Relationship Modelling on Bounded Spaces with Application to the Estimation of Forest Foliage Cover By Landsat Satellite ETM+ Sensor

Integrated Image Detection Algorithms for Robust Object recognition

Delivery of Social Services in an Restructing Region

Modelling with the Generalised Lambda Distribution

Estimation of the binomial parameter: In defence of Bayes (1763)

Interval estimation of the Binomial parameter π, representing the true probability of a success, is a problem of long standing in statistical inference. The landmark work is by Bayes (1763) who applied the uniform prior to derive the Beta posterior that is the normalised Binomial likelihood function. It is not well known that Bayes favoured this 'noninformative' prior as a result of considering the observable random variable x as opposed to the unknown parameter π, which is an important difference.

This thesis develops additional arguments in favour of the uniform prior for estimation of π. Specifically, it is shown that the so-called highest posterior density interval derived from the corresponding posterior appears to be preferable to any other intervals that have been proposed, when judged by both unconditional or frequentist and conditional or Bayesian properties.

Analysing and reporting Clinical Indicator Data using Hierarchical models

Hierarchical Bayeisan Models provided a method of developing interpretable measures of the potential to improve health care utilising the variation between hospitals rather than simply ranking and comparing the individual hospitals

Statistical methods for assessing and improving quality in hospitals

Awareness of the issues relating to hospitals means that health care practitioners need to have a working knowledge of methods available to assess and improve quality. This thesis developed frequentist and bayesian approaches to control charting, risk adjustment and comparing event rates.

• MPhil: Modelling with the Generalised Lambda Distribution
• MSc: Statistical Techniques for Improving Health Care
• PhD: Delivery of Social Services in an Restructing Region
• PhD: Application of Smooth Tests of Goodness of Fit to Generalised Linear Models
• PhD: Demand Forecast with Time Series Data Mining Approach