Postgraduate Course: Likelihood and Generalized Linear Models (MATH11121)
|School||School of Mathematics
||College||College of Science and Engineering
||Availability||Not available to visiting students
|Credit level (Normal year taken)||SCQF Level 11 (Postgraduate)
|Home subject area||Mathematics
||Other subject area||None
||Taught in Gaelic?||No
|Course description||The concept of likelihood is central to statistical inference. This course develops likelihood methods for single parameter and multiparameter problems, including iterative maximum likelihood estimation, likelihood-based confidence regions and likelihood ratio tests.
An important application of likelihood methods is to generalized linear models which provide a broad framework for statistical modelling of discrete or continuous data. Special cases of such models are considered.
Course Delivery Information
|Delivery period: 2013/14 Semester 2, Not available to visiting students (SS1)
||Learn enabled: Yes
|Course Start Date
|Breakdown of Learning and Teaching activities (Further Info)
Lecture Hours 22,
Seminar/Tutorial Hours 8,
Summative Assessment Hours 2,
Programme Level Learning and Teaching Hours 2,
Directed Learning and Independent Learning Hours
|Breakdown of Assessment Methods (Further Info)
|Main Exam Diet S2 (April/May)||MSc Likelihood and Generalized Linear Models||2:00|
Summary of Intended Learning Outcomes
|1. Familiarity with a wide range of statistical modelling situations.
2. Ability to apply likelihood based inference to real modelling situations.
3. Ability to apply likelihood methods to derive estimates, confidence regions and hypothesis tests.
4. Familiarity with examples of generalized linear models.
5. Ability to use R for statistical modelling and data analysis.
6. Ability to analyse data and interpret results of statistical analyses.
|See 'Breakdown of Assessment Methods' and 'Additional Notes', above.|
||This syllabus is for guidance purposes only :
1. Statistical modelling and applications of likelihood.
2. Likelihood principles.
3. Likelihood based inference for single parameter and multiparameter models.
4. Wald, score, and likelihood ratio tests and related confidence regions.
5. Generalized likelihood ratio tests.
6. Applied aspects of maximum likelihood estimation, including graphical approaches, iterative estimation and the method of scoring.
7. Statistical modelling using generalized linear models, link functions and exponential family distributions.
8. Several examples of generalized linear models, including normal, Poisson, exponential, gamma and binary regression.
9. Diagnostic and residual analyses for generalized linear models.
10. Using R to fit and assess models.
||1. Azzalini, A., (1996). Statistical Inference Based on the Likelihood. Chapman & Hall, London.
2. Pawitan, Y. (2001). In All Likelihood: Statistical Modelling and Inference using Likelihood. Oxford University Press, Oxford.
3. Dobson, A.J. (2002). An Introduction to Generalized Linear Models, 2nd Edition. Chapman & Hall/CRC, London.
4. McCullagh, P. & Nelder, J.A. (1989). Generalized Linear Models, 2nd Edition. Chapman & Hall, London.
|Course organiser||Dr Bruce Worton
Tel: (0131 6)50 4884
|Course secretary||Mrs Frances Reid
Tel: (0131 6)50 4883
© Copyright 2013 The University of Edinburgh - 10 October 2013 4:53 am