| Module Code | ST8003 |
| Module Name | Linear Regression |
| ECTS Weighting[1] | 10 ECTS |
| Semester taught | Semester 2 |
| Module Coordinator/s | Dr John McDonagh |
Module Learning Outcomes
On successful completion of this module, students will be able to:
MLO3.1 To carry out an initial examination of the data to determine an
appropriate regression model to use.
MLO3.2 To use a regression package (R) to apply multiple regression to
simple data sets.
MLO3.3 To produce and interpret graphs for data summary and model
diagnostics,
MLO3.4 To interpret the results of the model and see such modelling as the
basis for more advanced statistical analysis.
MLO3.5 To construct and exploit derived variables, such as logs, products
and indicator variables
Module Content
Specific topics addressed in this module include:
Review of simple linear regression model: assumptions, model fitting,
estimation of coefficients and their standard errors
The multiple linear regression model and its analysis including:
Confidence intervals and statistical significance tests on model parameters
Issues in the interpretation of the multiple parameters
Analysis of variance in regression: F-tests, r-squared
Indicator variables and interaction terms
18
Model validation: residuals, residual plots, normal plots, diagnostics
Introduction to logistic regression
Teaching and learning Methods
Assessment Details
The module is assessed by a series of practical tasks (50%) and a final
project (50%)
Reassessment Details
Contact Hours and Indicative Student Workload
This module has 7 weekly sessions that students work on in Weeks 1-7 of
Hilary Term. The session will be released the Friday before the start of that
week, with the synchronous session taking place on the Thursday or Friday
of the week.
Session 1 What is regression? Simple linear regression and the
principle of least squares. Diagnostics.
Session 2 Multiple linear regression, including confidence intervals,
hypothesis tests and prediction.
Session 3 Implementing regression in R and interpreting the output
Session 4 Pre-processing data for better analysis: transformations and
multi-collinearity.
Session 5 Analysis of Variance: regression when the variables are
discrete. Adding indicator variables and interactions to a regression
analysis.
Session 6 Introduction to logistic regression. Choosing a regression
model. .
Session 7 Implementing ANOVA and logistic regression in R and
interpreting the output
Recommended Reading List
Core reading materials. The core reading material is of course the module
study notes. These texts complement that material:
Sheather, S. J. A Modern Approach to regression with R,, New York:,
Springer 2009
Neter, J., Wasserman, W. & Kutner, M.H. Applied Linear Models , 2nd edition
Boston, Irwin:1989
Kutner. M. H., Nachtsheim, C.J., Neter, J. & Li, W. Applied Linear Statistical
Models, 5th, Boston: McGraw-Hill, 2005
Davies, “The Book of R: A First Course in Programming and Statistics”, 1st edition. Published by No
Starch Press.
The R project website has an extensive online manual at https://cran.r-project.org/manuals.html,
including material on regression
Supplementary reading or similar materials:
James, Witten, Hastie and Tibshirani, “An Introduction to Statistical Learning: with Applications in R.
Module Pre-requisites
Prerequisite modules: None.
Other/alternative non-module prerequisites: None.