Statistical data modelling

This unit explores the statistical modelling methods that underlie the analytic aspects of Data Science and Machine Learning. By working through examples, this unit gives a strong mathematical and statistical foundation to enable a deeper understanding of data analysis and machine learning methods taught in later MDS/MAI units which focus on machine learning with a more practical perspective. It introduces basic notions about data and foundational mathematics and statistics in the form of sample statistics, probability, expectation and parametrised probability distributions. This provides a basis to introduce statistical inference through maximum likelihood estimation, confidence intervals and hypothesis testing as a way of inferring information about the probability distributions that best describe observed data. Building upon inference models, the unit considers predictive models that predict one data variable based on other data variables through introductory supervised machine learning methods for regression and classification. Unsupervised machine learning methods such as clustering that find hidden groupings in data are also considered.

Active learning

Minimum total expected workload to achieve the learning outcomes for this unit is 144 hours per semester typically comprising a mixture of scheduled online and face to face learning activities and independent study. Independent study may include associated reading and preparation for scheduled teaching activities.