Postgraduate Course: Longitudinal Data Analysis (PGSP11487)
Course Outline
School | School of Social and Political Science |
College | College of Arts, Humanities and Social Sciences |
Credit level (Normal year taken) | SCQF Level 11 (Postgraduate) |
Availability | Available to all students |
SCQF Credits | 20 |
ECTS Credits | 10 |
Summary | There is now a great deal of longitudinal data available to social science researchers and many questions, particularly those that consider temporal relationships, are better addressed using longitudinal rather than cross-sectional data. This course is designed to introduce students to a variety of statistical approaches to analyzing longitudinal data. The course will have a practical focus and introduce students to analyzing existing large-scale household panel datasets. These datasets will include the British Household Panel Survey and Understanding Society (the UK Household Longitudinal Survey). The course will be taught using Stata software. |
Course description |
Topics covered
1. Introduction to longitudinal data and longitudinal data analyses
2. Examples of existing longitudinal datasets (e.g. the British Household Panel Survey; Understanding Society the UK Household Longitudinal Study)
3. Approaches to longitudinal data analysis (e.g. repeated cross-sectional analysis; cohort analysis; panel modelling; duration analysis; dynamic models)
4. Managing longitudinal social survey data analysis (e.g. understanding the workflow)
5. Using Stata software to analyze longitudinal data
6. Exploring existing longitudinal data
7. Modelling longitudinal data
8. Interpreting results from longitudinal data analyses
9. Presenting results from longitudinal data analyses
|
Entry Requirements (not applicable to Visiting Students)
Pre-requisites |
|
Co-requisites | |
Prohibited Combinations | |
Other requirements | None |
Information for Visiting Students
Pre-requisites | None |
High Demand Course? |
Yes |
Course Delivery Information
|
Academic year 2021/22, Available to all students (SV1)
|
Quota: 25 |
Course Start |
Semester 2 |
Timetable |
Timetable |
Learning and Teaching activities (Further Info) |
Total Hours:
200
(
Seminar/Tutorial Hours 20,
Programme Level Learning and Teaching Hours 4,
Directed Learning and Independent Learning Hours
176 )
|
Assessment (Further Info) |
Written Exam
0 %,
Coursework
100 %,
Practical Exam
0 %
|
Additional Information (Assessment) |
1. Components of Assessment:
75 % A short research report on a substantive topic (following from their research plan) containing the application of a suitable advanced statistical technique The overall report should be about 6 pages long and include 2,000 words that accompany the statistical output. This may appear shorter than a standard (e.g. theoretical) essay on a 4th year course, however the emphasis is on the application of an advance statistical technique. The report will mainly comprise of tables of summary information and statistical modelling outputs. the MSc version of this course will allow students to download/use any longitudinal dataset rather than a prepared dataset as at honours level facilitating the Data enabling test below. Informal one-to one meetings with students will provide additional support to undertake this additional element at MSc level.
5% An annotated Stata syntax (.do) file which fully replicates the analysis of the research report. There is no limit for the length of the .do file, but parsimony and elegance of programming will be encouraged.
20% Data enabling test. This will access the students ability to perform a range of tasks and operations that are germane to the analysis of longitudinal data. This assessment in not in the undergraduate version of the course. The rationale for this assessment is that genuine social surveys almost always require some preparatory work before analyses can be undertaken. We use the term data enabling to describe this phase of the workflow. In reality, even appropriately curated social science datasets will require some work to be undertaken to enable data analyses, even if only recoding some variables or coding some missing values. Longitudinal datasets are almost never provided in a form that renders them immediately ready for comprehensive analyses. Social scientists face many practical difficulties when enabling longitudinal data for analyses. The most obvious challenge is linking up individuals at multiple time points. Less obvious are the difficulties associated with matching individuals with others in the study, for example spouses, children, siblings or other household sharers. Many research questions also require the addition of important contextual information, for example about the household or locality, which can also prove challenging.
A substantial but often under-appreciated aspect of working with longitudinal datasets is the challenge of constructing appropriate measures which aid comparability over time or which suitably reject social changes. There are often a number of different measures (e.g. different socio-economic classifications) in the dataset that could be used, and often metadata are also supplied with the dataset. A weakness of some analyses is that they do not take full advantage of the richer data resources available in the survey because they are restricted to exploiting only the most readily available information. Therefore, developing suitable data enabling skills is an essential part of the skills portfolio for postgraduate researchers, especially those who plan to undertake dissertations or doctoral research with large-scale datasets.
The three components of the assessment above clearly meet the level 11 criteria. They require that the student has a critical overview of the subject and understands the principal theories and key concepts. The assessment will allow the student to apply a range of specialist data analysis skills that are appropriate to social research. The assessment will allow the student to demonstrate their critical understanding of numerical and graphical data. The assessment requires that the student clearly communicate research results. The assessments require that the students demonstrate that they have substantial authority and exercise a high level of autonomy and initiative in their work.
|
Feedback |
Verbal feedback will be given throughout the course.
Written feedback will be given on the assignments.
A completed and annotated version of the test will be published on Learn.
Informal one-to one meetings will be made available during the data enabling phase.
|
No Exam Information |
Learning Outcomes
On completion of this course, the student will be able to:
- Exercise substantial autonomy and initiative in the organisation and management of large and complex longitudinal datasets
- Critically assess the suitability of variables and measures within complex longitudinal datasets for social science research
- Creatively and independently plan and design a study using existing longitudinal data
- Undertake critical analysis of longitudinal data using statistical models
- Creatively cast scientific questions in longitudinal terms and interpret and report related analyses of longitudinal data
|
Reading List
Core Text: Gayle, V. and Lambert, P. 2018. What is Quantitative Longitudinal Data Analysis? London: Bloomsbury Press. ISBN978-1-4725-1540-7
Davies, R.B. 1994. From Cross-Sectional to Longitudinal Analysis¿, in Analyzing Social and Political Change. Edited by A. Dale and R.B. Davies. London: Sage. ISBN: 0803982984. (An excellent chapter in excellent book).
Kohler, U. and Kreuter, F. 2009. Data Analysis Using Stata (Second Edition). College-Station Texas: Stata Press. ISBN 9781597180467. (A very good book, ideal for students working in Stata).
Long, J.S. 2009. The Workflow of Data Analysis Using Stata. College-Station Texas: Stata Press. ISBN 9781597180474. (A great book on the practice of data analysis and data management).
Longhi, S., & Nandi, A. 2014. A practical guide to using panel data. Sage. ISBN-10: 1446210871. (A stellar tome!!).
Skrondal, A. and Rabe-Hesketh, S. 2004. Generalized Latent Variable Modelling: Multilevel, Longitudinal and Structural Equations Models. New York: Chapman and Hall. ISBN: 1-58488-000-7. (A very advanced, dense text which summarizes a wide array of statistical models which may be used for longitudinal analyses, highlighting the technical connections between them).
Singer, J.D. and Willett, J.B. 2003. Applied Longitudinal Data Analysis: Modelling change and event occurrence. New York: Oxford University Press. ISBN: 0-19-515296-4. (Wide coverage illustrating a selection of relatively advanced analytical strategies, although with less applied guidance than the title might suggest).
Taris, T. W. 2000. A Primer in Longitudinal Data Analysis. London: Sage. ISBN: 0761960260. (Excellent accessible explanations of many panel analysis methods)
Treiman, D. J. 2009. Quantitative Data Analysis ¿ Doing Social Research to Test Ideas. San Francisco: Jossey-Bass. ISBN: 9780470380031. (Overall an excellent book).
|
Additional Information
Graduate Attributes and Skills |
Generic cognitive skills (e.g. evaluation, critical analysis).
Communication, numeracy and IT skills.
Autonomy, accountability and working with others.
|
Keywords | Not entered |
Contacts
Course organiser | Prof Vernon Gayle
Tel: (0131 6)50 4069
Email: Vernon.Gayle@ed.ac.uk |
Course secretary | Mr Dave Nicol
Tel: (0131 6)51 1485
Email: dave.nicol@ed.ac.uk |
|
|