As health data becomes increasingly high-dimensional—spanning everything from patient records to genetic and spatial data—analysts need robust tools to uncover patterns, groupings, and relationships within these complex structures. Thes High-Dimensional Data Structures and Learning Algorithms module equips students with the knowledge and practical skills to analyse, interpret, and present such data using advanced statistical and machine learning techniques.
You will explore a wide range of methodologies, including logistic regression, discriminant analysis, principal component analysis, cluster analysis, multilevel models, and spatial regression. You will also be introduced to modern penalised regression and machine learning approaches suited for classification and dimension reduction, with all analyses carried out using R software.
The module emphasises research-connected teaching, with hands-on learning supported by real-world case studies drawn from current academic research. Weekly computer labs and journal clubs help students not only build digital fluency but also develop critical thinking and communication skills needed to evaluate published analyses and explain complex findings clearly.
Two authentic assessments simulate real-world tasks. In assessment 1, you will deliver a 15-minute oral presentation critically appraising the statistical methods used in an example published study (20%). In assessment 2, you will analyse a series of datasets using a variety of techniques and submit a detailed written report with critical discussion and interpretation of findings (80%).
Ideal for students aiming to become applied statisticians, data scientists, or healthcare analysts, this module builds a strong foundation in both theory and application—preparing you to tackle complex, high-volume data in any professional context.