Statistical Modelling using General Linear Models (GLMs)
Statistical modelling using generalised linear models (GLMs) is a free course for University of St Andrews research degree students (see eligibility advice below) and staff. The course covers extensions to linear models and generalised linear models; these models describe some form of response as a function of one, or more, explanatory variables and are powerful tools in understanding complex systems or predicting an outcome. The whole course is split into two parts (one part per semester) and participants can do one or both parts (see entry requirements).
The course is facilitated by St Leonard’s Postgraduate College and delivered by the Centre for Research into Ecological and Environmental Modelling (CREEM).
Content and Structure
Semester 1 (Part 1)
- Introduction and Extension of Linear Models
- A re-cap of multiple linear regression
- Generalized least squares and maximum likelihood
- Introduction to Generalised Linear Models
- Poisson response data
- For data with response values that are count
- Poisson response data
Semester 2 (Part 2)
Continuation of GLMs
- Binomial response data (also known as logistic regression)
- For data with response values that are proportions
- or binary (0 or 1 responses only)
- More advanced Generalised Linear Models
- Multinomial response data (also known as multiple outcome or multi-category models)
- data with unordered categorical responses (nominal), and
- ordered categorical responses (ordinal)
- Multinomial response data (also known as multiple outcome or multi-category models)
The course includes a substantial practical component and the methods covered will be implemented using the statistical programming environment R and RStudio.
The whole course is spread over semesters 1 and 2 and there will be a guided programme for self-study (see separate document for the course timetable). Course material (lecture notes, exercises and computer practicals) will be available online.
There will be an in-person introductory session to get you started and throughout the course there will be online help sessions, and a final in-person session to finish the course. You are encouraged to attend the introductory and final sessions in-person to meet the course tutor and provide feedback. Participation in the help sessions is optional.
Your weekly time commitment is anticipated to be about 2-3 hours learning through the course notes and associated computer practical and attending the optional help session.
There is an option for participants to obtain a certificate for each part by attempting all assessed quizzes and obtaining a pass. See the course timetable for the deadline for submitting responses to the assessed quizzes.
Timetable
Read the Statistical Modelling – Timetable (Word, 19 KB).
Each week there will be the option of joining a live (online) one-hour help session with a course instructor. See the course timetable for the date and time. During the session, the practicals will be introduced and the instructor will remain online during which time you may work at your own pace through the notes, on the practicals or ask questions. Questions may also be asked outside this time slot on the Teams channel.
Entry Requirements and Prior Learning
The prerequisites for this course are:
- to understand basic statistics in particular, hypothesis testing and simple linear regression. The “Introduction to Statistics” course would be an ideal introduction (and should be completed before enrolling on this course).
- be able to write basic commands in R to undertake an exploratory data analysis, fit simple linear regression model and interpret the R output.
You are encouraged to install R and RStudio on your laptop before the course starts.
Eligibility
The course is for University of St Andrews staff, and students matriculated on a doctoral degree or the following research degree programmes – MSc (Res), MSt (Res), and MPhil (by research).
The course is not open to students on an undergraduate degree or to students on a taught postgraduate degree programme (MSc, MLitt, or MRes).
Book Your Place
You can enrol on the course through the Personal Development Management System (PDMS). Course code 13893.
If you have any questions, please contact St Leonard’s Postgraduate College via email [email protected].