Advanced Statistics MSc
Flexible Regression (Level M) STATS5052
- Academic Session: 2026-27
- School: School of Mathematics and Statistics
- Credits: 10
- Level: Level 5 (SCQF level 11)
- Typically Offered: Semester 1
- Available to Visiting Students: Yes
- Collaborative Online International Learning: No
- Curriculum For Life: No
Short Description
This course introduces the theory and application of advanced regression models including non-linear, nonparametric and generalised additive models.
Timetable
Lectures: 20 lectures (2 hours per week, at times to be arranged)
Tutorials: fortnightly (at times to be arranged)
Practicals: 2, two hour computing sessions (at times to be arranged)
Excluded Courses
STATS4040 Flexible Regression
Assessment
Assessment
90-minute, end-of-course examination (85%)
Project (15%)
Main Assessment In: April/May
Are reassessment opportunities available for all summative assessments? No
It is the default expectation that all courses will offer opportunities for reassessment or deferred assessment. Where it is not possible to offer this in some assessment components, the grade achieved at the first attempt will be counted towards the final course grade, and any exceptions for this course are described below.
[No exceptions]
Course Aims
To develop the theory and application of advanced regression modelling by introducing students to non-linear, nonparametric and generalised additive modelling.
To introduce the idea of smoothing in a regression context.
To introduce a variety of approaches for smoothing including local polynomial regression and regression splines.
To explain and illustrate the appropriate uses and restrictions of advanced regression models.
To develop appropriate methods for the construction, selection and evaluation of advanced regression models.
To illustrate to students the application of advanced regression models in a variety of practical contexts.
Intended Learning Outcomes of Course
By the end of this course students will be able to:
■ formulate advanced regression models including non-linear, non-parametric and generalised additive models;
■ state, describe and compare methods for smoothing in a regression context;
■ describe techniques to choose smoothing parameters;
■ state expressions for degrees of freedom of a smoother;
■ apply smoothing in a wide variety of practical regression contexts;
■ describe methods to fit advanced regression models;
■ use hypothesis tests and appropriate criterion for model selection;
■ assess the goodness of fit of an advanced regression model;
■ fit advanced regression models in R;
■ interpret the output of R procedures for advanced regression models.
■ implement advanced regression methods using R and write a clear, concise report summarising their results.