PhD candidate, Mathematical Sciences (Statistics)
Research Training Program (RTP) Stipend
BSc (Hons) in Statistics, University of Queensland, 2014
Title: Assessing the accuracy of record matching algorithms in data linkage
The main focus of the project is to find various techniques to assess the accuracy of matching in data linkage. Data linkage is the statistical matching of records from two different sources (e.g., the Census and various health registries or Centrelink datasets) to create a larger and more powerful dataset. To ensure that matched records in the combined file actually correspond to the same individual is crucial for the validity of any analyses based on the combined data. The research work will be on assessing the likelihood that records matched from the two files actually belong to the same individual.
- Probabilistic Record Linkage
- Markov Chain Monte Carlo
- Bayesian Statistical Modelling
- Mixture Models
- Spatial Data Analysis
- Haque, Shovanur and Stern, Steven. Assessing the accuracy of record linkages with Markov Chain based simulation approach. The annual conference, 2015, organised by the Bayesian Research & Applications Group (BRAG) in collaboration with ARC Centre of Excellence for Mathematical & Statistical Frontiers (ACEMS); the Australasian chapter of the International Society for Bayesian Analysis (ISBA); the Statistical Society of Australia, Inc. (SSAI) Bayesian Statistics Section; and Queensland University of Technology (QUT) – Bayes on the Beach, Gold Coast, Australia 7-9 December 2015. URL https://botb2015.files.wordpress.com/2015/07/conference-program-bob-2015-final4.pdf, page 36.