Niamh is a statistician working at the interface of ecology, epidemiology, and data science. Her research focuses on applying and developing statistical and machine learning methods to address real-world challenges such as estimating species population sizes from count and trace data and predicting livestock disease re-emergence using sparse or imbalanced datasets. She works with a wide array of statistical approaches, including Bayesian hierarchical models, N-mixture models, anomaly detection algorithms, and spatial analysis techniques.
Niamh earned her PhD in Statistics, with a focus on multispecies abundance modelling, and holds a first-class MSc in Data Science. Alongside her research, she is actively engaged in science communication and education, running a popular blog on applied statistics for non-specialists, and regularly delivering workshops and guest lectures on topics such as GLMs and machine learning with imbalanced data.
Education & Career
- PhD in Statistics (Multispecies Abundance Modelling)
- MSc in Data Science (First Class Honours)
- Instructor, consultant, and science communicator in statistical ecology and epidemiology
Research Focus
Niamh’s work centres on extracting meaningful insights from complex ecological and epidemiological data. She is particularly interested in population estimation techniques and predictive modelling for conservation and disease management, using advanced statistical tools and reproducible workflows.
Current Projects
- Development of Bayesian and ML approaches for estimating species abundance from imperfect data
- Modelling livestock disease risk using spatial and temporal predictors
- Creating accessible educational materials for teaching applied statistics in R
Professional Consultancy
Niamh provides expert statistical support to academic and applied research projects, with a focus on ecological monitoring, conservation planning, and disease modelling. She also advises on study design and data workflows for interdisciplinary teams.
Teaching & Skills
- Teaches topics including GLMs, Bayesian statistics, machine learning for imbalanced data, and spatial statistics in R
- Advocates for reproducibility, open science, and accessible statistical training
- Experienced in communicating complex methods to broad audiences
Links
5.0
