Undergraduate Course: Multi-Level Modelling in Social Science (SSPS10024)
|School||School of Social and Political Science
||College||College of Arts, Humanities and Social Sciences
|Credit level (Normal year taken)||SCQF Level 10 (Year 3 Undergraduate)
||Availability||Available to all students
|Summary||The course enables students to understand and use multilevel models mainly in the context of social science, but examples are also given from medicine and some aspects of biological science. The focus is on multilevel models for quantitative, binary and multinomial outcomes, with shorter sessions on models for ordinal and count outcomes. The importance of multilevel modelling for longitudinal data is explained. Analysis is conducted using the Noteable service and the R Stan statistical modelling package, which is free to all users. Lectures are combined with practical sessions in order to reinforce concepts.
Multilevel models are becoming an increasingly popular method of analysis in many areas of social science, medicine and natural science. There are many situations where an improved analysis is obtained compared to single level models, both in terms of improved statistical fit to the data, and also improving our understanding of social structures and policy interventions versus individual-level analysis.
Potential advantages include:
- the scope for wider inference: for example in a study of school attainment, the different association between the outcome at individual, class, school and education authority can potentially be understood;
- similarly, the relationship between an outcome of interest for individuals, households and their area-level context can be analysed;
- more appropriate mean estimates, when the effect of spurious outlying results for small groups are reduced;
- a more efficient analysis with smaller standard errors, particularly when there are few observations per group;
- avoidance of problems caused by missing outcomes: this is an advantage in longitudinal studies (for example panel studies) where there are often dropouts;
- use of more appropriate variances and correlations: for example in a longitudinal analysis the correlation between observations on the same person may become less for measurements that are further apart in time.
The course enables you to understand and use multilevel models mainly in the context of social science, but examples are also given from medicine and some aspects of biological science. The focus is on multilevel models for quantitative, binary and multinomial outcomes, with further sessions on models for ordinal and count outcomes. The importance of multilevel modelling for longitudinal data is explained Analysis is conducted using the Noteable service and the R Stan statistical modelling package, which is free to all users.
Most of your learning will be in practical work. As well as the labs run in the weekly practical sessions, a teacher will be available for consultation, and I offer bookable office hours.
Entry Requirements (not applicable to Visiting Students)
|| Students MUST have passed:
Statistical Modelling (SSPS10027)
|Prohibited Combinations|| Students MUST NOT also be taking
Multi-Level Modelling in Social Science (PGSP11424)
||Other requirements|| For those students who are required to take a Quantitative Methods course as part of their degree programme, this course can be counted towards that condition.
Information for Visiting Students
|High Demand Course?
Course Delivery Information
|Academic year 2022/23, Available to all students (SV1)
|Learning and Teaching activities (Further Info)
Lecture Hours 10,
Seminar/Tutorial Hours 10,
Programme Level Learning and Teaching Hours 4,
Directed Learning and Independent Learning Hours
|Assessment (Further Info)
|Additional Information (Assessment)
||A guided exercise around week 6 of the course worth 25% of the course grade. This assignment will involve students running, reporting and briefly interpreting a set of multilevel models which will use a continuous outcome. Models covered will include variance component, random intercept and random slope.
An end-of-course practical project, worth 75% of the total marks for the course. Students will be given a choice of one of three data sets to analyse, and some questions about each of them. The main focus of the project will be on social scientific questions which will have to be answered using multilevel models. The dependent variables in these projects will offer more challenge (than the mid-semester assignment) by being be non-normal (for example, categorical or count) additionally longitudinal or multivariate outcomes might be used.
||There will be a formative assessment early in the course using single level regression. This will give students a chance to check their familiarity with relevant statistical software, and to get early feedback on the presentation of statistical results.
|No Exam Information
On completion of this course, the student will be able to:
- describe the conceptual and mathematical basis of multilevel models.
- estimate multilevel models in an appropriate software package.
- to cast scientific questions in multilevel terms.
- to interpret and communicate the results of multilevel models clearly.
|Graduate Attributes and Skills
||Developing advanced quantitative skills and the capacity to use them in applied scientific context.
|Keywords||Multi-level modelling; regression; longitudinal data.
|Course organiser||Dr Orian Brook
|Course secretary||Mr Ethan Alexander
Tel: (0131 6)50 4001