We use cookies to ensure that we give you the best experience on our website. You can change your cookie settings at any time. Otherwise, we'll assume you're OK to continue.

Durham University

Wolfson Research Institute for Health and Wellbeing

Previous Events

WASP 2 : Applied Linear Regression (4 day course)

10th November 2014, 10:10 to 13th November 2014, 16:30

This course is limited to 20 people and as such registration is essential.

Internal Delegates (Staff/Students of Durham University) – Free of Charge

External Delegates – £400, inclusive of lunch each day and all course materials.

Please use this link to register. 

This module will introduce advanced concepts and applications of linear regression models. It will start with simple linear regression with only one predictor. The difference between correlation and regression models will be revisited. For categorical predictors, linear regression models will be compared to analysis of variance with an emphasis on the generalisation of the methods as linear models. The regression assumptions and remedials will be discussed. The module will introduce multiple linear regression models with more than one predictor. The implication of multiple predictors on the interpretation of the regression results will be highlighted. The challenge of multicollinearity for continuous predictors and confounders for categorical predictors will be illustrated with real data. Regression diagnosis for outliers and influential cases will be present with suggestions on how to minimise their effects. The final part of the module will emphasise the principle of model building and variable reduction with a focus on parsimony without the loss of the research question.

Specific Topics

  •  Linear regression with one continuous predictor
  •  Linear regression with one categorical predictor
  • Regression assumptions and remedial measures
  • Regression with more than one continuous predictors
  • Regression with more than one categorical predictors
  • Interaction between two categorical predictors
  • Interaction between categorical and continuous predictors
  • Model selection and variable reduction
  • Understanding multicolinearity and remedial
  • Understanding outliers and influential cases


This module requires participants to have previous knowledge of basic statistics and quantitative methods such as t-tests, simple linear regression and ANOVA. Participants will be required to demonstrate they have taken our course on Basic Stats or any other relevant quantitative course.


9.30 - 10.00

Day 1

Registration and Coffee - D017

Day 2

Registration and Coffee - D012

Day 3

Registration and Coffee - D018

Day 4

Registration and Coffee - D018

10:00 –12:00 Simple Linear regression - D025 Multiple linear regression (I) - D026 Multiple linear regression (III) - D026 Model building (II) - D026
12:00 – 13:00 Lunch - Waterside Restaurant Lunch - Waterside Restaurant Lunch - Waterside Restaurant Lunch - Waterside Restaurant
13:00 – 15:00 Diagnostic and remedial measures - D025 Multiple linear regression (II) - D026 Model building (I) - D026  Model building (III) - D026
15:00 – 15:30 Coffee break - D017 Coffee break - D358 Coffee break - D018 Group presentations - D026
15:30 – 16:30 Group work - D025 Group work - D026 Group work - D026

Please use this link to register. 

Contact for more information about this event.