Module Code - Title:
MS6061
-
FUNDAMENTALS OF STATISTICAL MODELLING
Year Last Offered:
2025/6
Hours Per Week:
Grading Type:
N
Prerequisite Modules:
Rationale and Purpose of the Module:
The purpose of this module is the development and application of statistical models with emphasis on linear and generalised linear models. The rational of this module is the equip MSc students with the theoretical and practical knowledge of a range of statistical models applied to real-world data, focusing on the accurate interpretation and communication of results. The module will use R to fit models to a wide range of datasets.
Syllabus:
General Linear Models: matrix formulation of the linear regression model, estimation of model parameters, regression residual diagnostics with emphasis on leverage and points of influence, multicollinearity, partial correlation and model fit statistics, transformations of the dependent and/or independent variables, mediation and moderation. Analysis of variance (ANOVA), two-way ANOVA, analysis of co-variance (ANCOVA).
Introduction to Generalised Linear Models including Binary Logistic regression, Poisson regression and Negative binomial regression.
Application of Generalised Linear Models to a complex data set: Determine an appropriate model to examine an outcome variable in a large real world data set. Critique potential models on the basis of model fit, residuals and interpretability.
Learning Outcomes:
Cognitive (Knowledge, Understanding, Application, Analysis, Evaluation, Synthesis)
Upon successful completion of this module students will be able to:
1. Communicate the role of linear and generalised linear modelling methodologies in data science.
2. Apply linear and generalized linear modelling methodologies to real world data using R.
3. Explain the underlying assumptions for linear and generalised linear models.
4. Perform diagnostic checks to identify potential problems in fitting statistical models to sample data.
5. Interpret the results of analyses, and communicate these clearly and concisely.
Affective (Attitudes and Values)
On successful completion of this module students will be able to:
1. Display best practice in statistical modelling for data science.
Psychomotor (Physical Skills)
NA
How the Module will be Taught and what will be the Learning Experiences of the Students:
The module will be taught using lectures and computer labs. This module will be informed by real-world datasets and datasets analysed in recent research publications. Graduate attributes for the MSc students will be developed by delivering new knowledge on advanced statistical methodologies, promoting responsible analysis and reporting of results, focusing on the proactive use of data to deliver good and reliable information, and directing articulate presentation and communication of analyses.
Research Findings Incorporated in to the Syllabus (If Relevant):
Prime Texts:
James Gareth, Daniela Witten, Trevor Hastie and Robert Tibshirani. (2018)
An introduction to statistical learning.
, Springer
John Fox and Sanford Weisberg. (2018)
An R companion to applied regression
, Sage
Other Relevant Texts:
Kleinbaum, David G., Lawrence L. Kupper, Azhar Nizam, and Eli S. Rosenberg. (2013)
Applied regression analysis and other multivariable methods
, Nelson Education
Programme(s) in which this Module is Offered:
Semester(s) Module is Offered:
Autumn
Module Leader:
Helen.Purtill@ul.ie