Skip to Content

Statistical Learning with Python - STAT868

Statistical learning refers to statistical methods that are suitable for the tasks of prediction and classification. Statistical learning methods can be divided into supervised and unsupervised learning. Supervised learning involves observations on the outcome variable and predictors but for unsupervised learning there is no outcome variable observations. For supervised learning, we will focus on nearest neighbours, linear and quadratic discriminate methods, logistic regression, neural networks, support vector machines and tree classification methods. For unsupervised learning, we will study cluster analysis, principal components analysis, factor analysis and independent component analysis.

An important special character of this unit, when compared with most machine learning units, is that students will learn systematically statistical reasons behind the popular statistical/machine learning methods. The programming language Python will be used in teaching this unit.

Credit Points: 4
When Offered:

TBD - Not offered in the current year; next offering is to be determined

Staff Contact(s): Statistics Staff

(Admission to MAppStat or GradDipAppStat) and (STAT806 or STAT810Prerequisite Information


Unit Designation(s):
Assessed As: Graded
Offered By:

Department of Mathematics and Statistics

Faculty of Science and Engineering

Course structures, including unit offerings, are subject to change.
Need help? Ask us.