What this programme is about
A PhD in Statistics is built around questions that existing statistical methods do not answer well enough.
Your research might focus on inference, Bayesian methods, high-dimensional data, causal analysis, time series, computation or another specialised area.
Most of the work is independent. You spend long periods reading papers, proving results, testing methods and finding out that an idea needs to be revised.
Programming and mathematics usually sit side by side. A method may look elegant on paper but still need extensive simulation before you understand how it behaves.
The goal is not to apply established techniques more efficiently, but to contribute something genuinely new to statistical theory, methodology or practice.
Supervisor fit matters enormously, so compare research groups, methodological strengths and the kinds of datasets or applications available before choosing a programme.
Inside the curriculum
Skills you'll build
Where this can take you
What studying this programme is like
Early doctoral work often includes advanced seminars in probability, inference and specialised statistical methods.
Your literature review helps you identify a gap that is narrow enough to investigate but important enough to justify several years of research. Methodological projects may involve proving theoretical properties, developing new estimators or building computational algorithms.
Applied statistics research can focus on health, finance, climate, social science or other fields where new methods are needed.
Simulation studies are commonly used to understand how methods behave under different assumptions.
The thesis must eventually show original statistical work that can withstand close theoretical and empirical scrutiny.
Is this likely to suit you?
Good fit if you...
- You have strong postgraduate mathematics and statistics foundations.
- You enjoy open-ended methodological problems.
- You are comfortable with programming and proofs.
- You want a research or academic career.
- You can work independently for long periods.
Think twice if you...
- You mainly want a practical analytics qualification.
- You dislike mathematical theory.
- You want a short, structured taught programme.
- You are not interested in producing original research.