Ian has been a statistical consultant for over 20 years.  His research focuses on applied statistics in a broad range of disciplines.  He is also a specialist in prediction error assessment.

At UTAS, Ian leads the statistics and data science services for TIA researchers and PhD students.

Biography

Ian has technical expertise and consulting experience in the following areas.

* Hypothesis testing and practical Bayesian inference.

* Data dimension reduction and re-structuring.

* Experimental design and ANOVA analysis.

* Survey analysis and design.

* Linear mixed models in pharmacology, psychology and medical trials.

* Non-parametric inference.

Ian has academic research experience in the following areas.

* Applied statistics and data science collaborations across many different disciplines.

* Forecast model selection, model over-fitting and expected prediction error analysis.

* Statistics and the law.

Career summary

Qualifications

Ian holds post-graduate degrees, with honours, from Université Catholique de Lille (France – Doctorate, 2020), the London School of Economics (London – MSc, 2006), City University (London - MSc, 2005) and Otago (New Zealand - PGDiAppStat, 1996).  He also has a post-grad certification in data science from MIT (USA – Micromasters, 2021).

Languages (other than English)

French and Spanish.

Memberships

Professional practice

Ian is a Chartered Statistician (CStat) and Fellow of the Royal Statistical Society.

Teaching

Teaching expertise

Ian has been the unit co-ordinator for lectures in statistics and computing for statistics (R, Python and Matlab) in France for five years and in Australia since 2019.  Ian has taught at undergraduate, MSc and PhD levels.

Ian is currently the unit co-ordinator for KLA201/310/439 (agri-food research methods).

Teaching responsibility

Ian's work is focused on expressing uncertainty in plain language, and explaining models and statistical inference to scientific researchers and “non-specialists”.

Ian's research specialities are in prediction models, assessing prediction errors and accounting for model.