Department of Statistics


Research areas

Our staff are engaged in ground breaking research which is recognised internationally. Read more about our areas of research below.

Biostatistics and novel regression methodologies


Statisticians at Auckland are developing new statistical methods for a whole range of problems, many of which originally came to the notice of the statistical community in a medical or biostatistical context, but whose solutions are generally applicable. Much of this work relates to forms of regression, i.e. to finding novel ways to understand or predict the behaviour of variables of compelling interest using information gathered on other variables.

Examples include models and generalised estimating equation methods to better understand correlated binary data, improved methods for longitudinal data analysis, using smoothing techniques to reveal relationships in multivariate data without making restrictive assumptions, adapting regression methods to allow novel approaches to sampling that can increase the efficiency of observational studies (e.g., generalisations of case-control sampling).

The people with the greatest involvement in these types of research are Yong Wang, Thomas Yee and Thomas Lumley, and we will soon welcome Claudia Rivera-Rodriguez. Several researchers are also actively involved in practical medical research, most notably Patricia Metcalf and Thomas Lumley. In the past Alastair Scott, Alan Lee, Chris Wild were major contributors to this area.

Top

Human Genomics and Bioinformatics


  • Yalu Wen is a statistical geneticist and bioinformaticist who studies the measurement of genetic and epigenetic features and the analysis of human genetic data.
  • James Curran has been co-Director of the Bioinformatics Institute, because of his research in forensic DNA analysis.
  • Thomas Lumley works on large-scale DNA sequencing and genetic association studies in human health, especially in cardiovascular disease.
  • Steffen Klaere conducts research on methods for estimating family trees of species, and also collaborates with Wine Science researchers as a bioinformaticist.

Top

Statistical computing


This Department is the birthplace of R (R is the language and environment for statistical computing and graphics) and home to a growing number of statisticians who do substantial work on statistical computing and computational statistics.

Find more information about the 'R' project

Standard commercial statistical packages are good for routine analyses of sets of data without non-standard features. Such data sets are rarer than you might think. Commercial packages are fast and implement algorithms and procedures that were seen to be viable at the time the package was written.

For statistical research one requires more flexibility than these packages generally provide. A statistician has an idea for a non-standard approach to the problem and wants to try it out. In these situations a more flexible system is required. It is not the time it takes the computer to execute the commands that is important but rather the time it takes the statistician to develop new software. Ongoing research and software development in the Statistics Department is building computing environments that increase the effectiveness and efficiency of the statistician. There is associated research on statistical graphics, on developing software to implement specific new statistical methods and on computer-intensive statistical methods such as Markov Chain Monte Carlo.

The people with the greatest involvement in these types of research are Ross Ihaka (joint founder of R along with then Department member Robert Gentleman), Paul Murrell (R Core Group developer with a primary interest in graphics), Brendon Brewer (Nested Sampling for Bayesian inference), Thomas Lumley, Thomas Yee, Yong Wang, and David Scott.

Find more information about software development

Top

The analysis of survey data


Over the years, researchers have been analysing data from complex surveys as if it came from random samples. The results of such analyses can be extremely misleading. Standard methods have to be adapted to allow for the special features of survey data.

Alastair Scott has been a world authority in this area for many years.  Thomas Lumley continues to work on theory for survey statistics and maintains the leading open-source software package. Research is also being conducted into novel ways of obtaining and analysing market research data, multilevel modelling, the effects of interviewer variability on subsequent analyses, and the design of panel studies. We have close connections with COMPASS, the Centre of Methods and Policy Application in the Social Sciences, which conducts social and health policy research using survey data. 

Senior Tutor Andrew Balemi talks about Market Research and why we buy what we buy

Top

Statistical Ecology and Bioinformatics


Our department has an extensive and world-renowned research group in statistical ecology, whose members have a broad range of areas of expertise and interests.

Building on the great legacy of George Seber, a senior professor and world authority on the estimation of animal abundances, we have Rachel Fewster, who works on statistical methods for population abundance assessment - how many whales are there in the ocean, or goats in the Hunua Ranges? She also works with models to investigate how a population spreads through its environment, for example rats colonizing islands off the NZ coast or rare birds surviving in a managed forest habitat.  Newly-arrived researcher Ben Stevenson has research in similar areas.

Russell Millar specialises in the modelling of marine fish populations from catch data. In particular, he uses recently developed likelihood and Bayesian techniques for analysing things like gear selectivity, fish growth and doing sequential population analysis.

Nick Shears combines marine ecological research and a variety of statistical techniques to address marine conservation and management questions, such as investigating how ecosystems respond to marine reserve protection and how sedimentation affects rocky reef assemblages.

Thomas Yee has made important contributions to statistical modelling in plant ecology and retains an active interest in the area.

James Russell applies statistical and genetic methods to problems in island conservation and ecology. He is an internationally recognised expert is the control of invasive species on islands.

Watch an interview with Rachel Fewster about Statistical Ecology and hear some amazing animal adventures

Top

Forensic Statistics


Statistical models are becoming increasingly important in forensic science. Our department has had a longstanding research partnership with ESR Forensic, the Crown Research Institute with primary responsibility for forensic science in New Zealand. ESR has provided scholarships for research students in our department and we have responsibility for teaching some courses in the MSc in the Forensic Science programme.

James Curran and Chris Triggs are interested in applications of statistics and population genetics in forensic science including DNA fingerprinting and the interpretation of physical evidence such as toolmarks, marks on ammunition, and fragmentary evidence from glass and fibres.

Forensic science at ESR

Watch an interview with James Curran using Forensic Statistics in a real legal case

Top

Statistics education


The department is internationally known for its statistics education research on statistical inferential reasoning, characterising statistical thinking in empirical enquiry, and developing students’ statistical literacy.

There are two active research programmes led by Maxine Pfannkuch. One project involved nine secondary teachers, Chris Wild, Matt Regan and a PhD student Pip Arnold, who have developed and trialled in Year 9 to 12 classrooms new dynamic visualisations and verbal interactions for conceptualising and reasoning inferentially. In October 2010 Chris Wild presented a paper from this research at the Royal Statistical Society in London.

A new project extends the work on statistical inferential reasoning to Year 13, the workplace, and undergraduate statistics and involves a total of 32 teachers, lecturers and researchers in New Zealand. The research is exploring innovative visualisations of bootstrapping and randomisation techniques to not only improve students’ statistical reasoning but also to provide accessible visuo-analytic conceptions of data to users of statistics in many fields of enquiry.

Stephanie Budgett is leading an exploratory project into statistical literacy for consumers of statistics. Chris Wild is a Past-President of the International Association of Statistical Education (IASE).

As part of an international project, the department is also recognised internationally through its hosting of the:

Nationally the department is recognised by the Ministry of Education for its research, as we are actively involved in the development of the new school statistics curriculum.

Watch an interview with Rachel Cunliffe who helped with the CensusAtSchool project

Top

Experimental design and quality improvement


The design and analysis of experiments is still a fertile research area. It has received renewed impetus because the emphasis quality improvement gives to using experimentation to obtain good quality data to make improvements, in areas where obtaining data is often extremely expensive. Improvements in computation have also allowed increased flexibility in choice of design and analysis.

We have several researchers working in this area. Arden Miller's research is in industrial experimental design. Kathy Ruggiero studies experimental design used in biological laboratory research. Chris Triggs is involved with agricultural experimental design.

Top

Operations Research and Stochastic Processes


Stochastic models of systems and their performance are important in many fields. The group at Auckland has a wide range of interests with varied applications:

  • Geoffrey Pritchard models fluctuations in the electricity market.
  • Ilze Ziedins works on performance analysis and optimal control of networks such as the Internet and telecommunications networks, and on improving the internal scheduling of Auckland's hospitals.
  • Rachel Fewster works on the modelling and control of predator populations such as rats, and other ecological problems.
  • Ciprian Giurcaneanu's research activity is focussed on the use of information theoretic methods in statistics, with a special emphasis on the modelling of time series.
  • David Scott is investigating an unusual class of flexible distributions with applications in finance and other areas.
  • Mark Holmes studies self-interacting random walks and related models in statistical physics.
  • Thomas Lumley is interested in the real-time modelling of Auckland's bus network.
Top

Bayesian Statistics


The department of Statistics has a strong Bayesian research group which is part of the Australian-NZ ARC Network on Bayesian Modelling and the International Society for Bayesian Analysis. Interdisciplinary collaborations in biology, bioinformatics, ecology, econometrics, engineering, fisheries, forensics, medicine and physics offer opportunities for keen graduate students to participate in cutting-edge research. Members of the group are working on philosophical aspects of Bayesian inference, applied Bayesian data analysis and highly computationally intensive Markov chain Monte Carlo (MCMC) simulation techniques.

  • Renate Meyer is working on Bayesian semi-parametric survival analysis techniques with applications in medical statistics and engineering, stochastic volatility models for analysing financial time series, population dynamics models for fisheries stock assessment and inverse problems of marine ecosystems, and MCMC techniques for cosmic microwave background and gravitational radiation data analysis in astrophysics. Methods derived from her work were used in the landmark gravitational-wave detection in 2016.
  • Russell Millar specialises in the modelling of marine fish populations from catch data. In particular, he uses recently developed likelihood and Bayesian techniques for analysing gear selectivity and fish growth and for sequential population analysis.
  • James Curran is interested in Bayesian models for forensic problems.
  • James Russell is interested in the application of Bayesian methods to complex ecological problems.
  • Brendon Brewer is interested in applications of Bayesian statistics in astronomical problems, and in software for efficient Bayesian computation.

International Society for Bayesian Analysis

Top