| CODE | SOR3211 | ||||||||
| TITLE | Generalized Linear Models | ||||||||
| UM LEVEL | 03 - Years 2, 3, 4 in Modular Undergraduate Course | ||||||||
| MQF LEVEL | 6 | ||||||||
| ECTS CREDITS | 4 | ||||||||
| DEPARTMENT | Statistics and Operations Research | ||||||||
| DESCRIPTION | - Exponential Family of Distributions - Generalized Linear Model and Link Function - Maximum Likelihood - Asymptotic Theory - Consistency - Asymptotic Normality - Connection with Method of Least Squares - Iterative Reweighted Least Squares algorithm - Inference - Sampling Distribution for Scores - Log-Likelihood Ratio Statistics - Hypothesis Testing - Residuals - Linear Models as a Special Case of Generalized Linear Model - Regression Model - Not-Full Rank Linear Regression Model - ANOVA Models - Logistic Regression Models - Binomial Logistic Models - Multinomial Logistic Models - Ordinal Logistic Models - Log-Linear Models and Contingency Tables - Poisson, Multinomial and Product Multinomial Probability Models - Maximum Likelihood Estimation - Iterative Proportional Fitting Algorithm - Hypothesis Testing - Goodness-of-Fit Tests Study-Unit Aims: - Familiarize with different Generalised Linear Models that accommodate any distribution within the exponential family; - Use the iterative reweighted least squares algorithm to estimate parameters; - Use diagnostic tools to identify model misspecifications, outliers, influential data points and collinearity. Learning Outcomes: 1. Knowledge & Understanding: By the end of the study-unit the student will be able to: - Define the assumptions of Generalised Linear Models on independence, distribution, linear predictor and link function; - Understand the limitation of Generalised Linear Models when the independence assumption is violated; - Identify alternative ways to address the problem of independence by using Generalised Estimation Equations or Multilevel models. 2. Skills: By the end of the study-unit the student will be able to: - Fit Generalised Linear Models identifying the appropriate distribution and link function; - Use Generalised Linear Models for prediction; - Use the change in deviance to assess goodness of fit and identify the parsimonious model; - Use diagnostic tool to identify outliers and model misspecifications. Statistical packages (MATLAB, SPSS) will be used throughout the course. Main Text/s and any supplementary readings: Suggested Texts: - Dobson, A. (1999) An Introduction to Generalized Linear Models, Chapman & Hall - McCullagh, P and Nelder J.A.(1998) Generalised Linear Models, Chapman & Hall |
||||||||
| ADDITIONAL NOTES | Pre-Requisite Study-Units: SOR1110, SOR2211 and SOR3221 | ||||||||
| STUDY-UNIT TYPE | Lecture and Practical | ||||||||
| METHOD OF ASSESSMENT |
|
||||||||
| LECTURER/S | Liberato Camilleri |
||||||||
|
The University makes every effort to ensure that the published Courses Plans, Programmes of Study and Study-Unit information are complete and up-to-date at the time of publication. The University reserves the right to make changes in case errors are detected after publication.
The availability of optional units may be subject to timetabling constraints. Units not attracting a sufficient number of registrations may be withdrawn without notice. It should be noted that all the information in the description above applies to study-units available during the academic year 2023/4. It may be subject to change in subsequent years. |
|||||||||