Analysis of Categorical Data
5 credits
Syllabus, Master's level, 1MS370
A revised version of the syllabus is available.
- Code
- 1MS370
- Education cycle
- Second cycle
- Main field(s) of study and in-depth level
- Mathematics A1N, Mathematics A1N
- Grading system
- Fail (U), Pass (3), Pass with credit (4), Pass with distinction (5)
- Finalised by
- The Faculty Board of Science and Technology, 10 March 2016
- Responsible department
- Department of Mathematics
Entry requirements
120 credits including 90 credits in mathematics, including Regression Analysis.
Learning outcomes
In order to pass the course the student should be able to
- give an account of the sampling strategies for categorical data;
- analyse a two-way contingency table;
- carry out exact inference for a three-way contingency table;
- build and apply logit and loglinear models;
- use R for analysing real data sets;
- be able to interpret the results in practical examples.
Content
Poisson sampling. Binomial sampling. Inference for odds ratio. Chi-squared tests. Fisher's exact test. Partial tables. Cochran-Mantel-Haenszel methods. Exact tests. Models for binary data. Loglinear models for contingency tables. R commands.
Instruction
Lectures and computer sessions.
Assessment
Written examination at the end of the course. Compulsory assignments during the course.