Undergraduate Course: Data Analysis (MATH10011)
|School||School of Mathematics
||College||College of Science and Engineering
|Credit level (Normal year taken)||SCQF Level 10 (Year 4 Undergraduate)
||Availability||Available to all students
|Summary||Course for Honours Degrees involving Statistics. Note that this course is not about 'Big Data'.
The syllabus may change from year to year according to what other courses in Statistics are offered, but it is likely to contain most of the following topics.
1. Two-way and three-way classifications, blocking, interaction
2. Models with categorical and continuous variables, analysis of covariance
3. Generalized linear models for binary and count data
4. Repeated measures, emphasising the use of summary statistics
5. Random effect models, emphasising REML estimation for Normal models
6. Non-linear regression
This course builds on the material on linear models for continuous response variables that was considered in Linear Statistical Modelling (MATH10005) in order to examine more complex structures, including data with two or more factors and with both factors and continuous explanatory variables. The generalized linear models for binary and count data that were introduced in Likelihood (MATH10004) are extended in a similar way. Methods are also introduced for repeated measures: these comprise sequences of responses recorded on the same individual or object. Other extensions of linear statistical models that are considered are to non-linear regression and to models in which random variation in the response is assumed to arise from several sources.
In parallel with the lectures, students attend practical sessions in which they learn about the statistical language R, and use R to plot and summarise data sets, to fit models of the types discussed in the lectures, and to draw conclusions about the data. Output from R is included in reports that are submitted roughly fortnightly, and returned to their authors with marks and written comments: this allows students to learn from the feedback on their work before the next report is prepared. The first of these reports is for practice, and the remainder form the basis for the assessment of the course. Students are encouraged to confer on their analyses of the data, but their reports should be their own work.
Information for Visiting Students
|High Demand Course?
Course Delivery Information
|Academic year 2015/16, Available to all students (SV1)
|Learning and Teaching activities (Further Info)
Lecture Hours 19,
Supervised Practical/Workshop/Studio Hours 16,
Programme Level Learning and Teaching Hours 4,
Directed Learning and Independent Learning Hours
|Assessment (Further Info)
|Additional Information (Assessment)
|No Exam Information
On completion of this course, the student will be able to:
- Knowledge of R commands for plotting and annotation (including methods for repeated measures), fitting and examining linear and generalized linear models, model selection, calculating summary statistics for repeated-measures data, variance component estimation, non-linear regression.
- Ability to choose and apply appropriate statistical models and methods for the topics listed in the Syllabus Summary.
- Ability to prepare typed reports of statistical analyses using LaTeX (or MS Word) and selected R output.
|Course organiser||Dr Chris Theobald
Tel: (0131 6)51 7032
|Course secretary||Mrs Alison Fairgrieve
Tel: (0131 6)50 5045
© Copyright 2015 The University of Edinburgh - 18 January 2016 4:24 am