Statistical Services Centre Ltd
  • Home
  • Training
    • Course Registration
    • Terms and Conditions
    • Bespoke Training
    • Mailing List Request
  • Consultancy
    • Expertise
  • Team
    • James Gallagher
    • Sandro Leidi
    • Dankmar Böhning
  • SSC-Stat
  • Resources
  • Contact us
  • Products

Statistical Modelling in Epidemiology

Overview
Non-model-based statistical analysis methods have been popular in epidemiology.  Among these have been stratified analyses to adjust for a potential confounding variable, in particular Mantel-Haenszel type methods for analysing binary outcomes.  While such analysis methods are still commonly used, they lack the flexibility offered by a statistical model.  Statistical models can be used to adjust exposure effects for different types of confounding variables simultaneously, and easily provide an assessment of effect modification.  Further, in addition to hypothesis testing, the modelling approach easily provides estimates of effect measures and corresponding confidence intervals.
This course will introduce commonly-used statistical modelling techniques.  The emphasis will be on practical application, rather than theoretical results.  Presentations and hands-on computer practicals will use the statistical package Stata.

Who Should Attend?
Medical or public health professionals working in epidemiology who already have some statistical knowledge, but wish to be conversant with the concepts and applications of statistical modelling.  Prior attendance on Introduction to Epidemiological Methods, or equivalent knowledge, is required for this course.  Participants will be assumed to have an elementary knowledge of Stata.

How You Will Benefit
You will be introduced to common statistical modelling techniques that are applicable in epidemiology, learn about the flexibility of a statistical model and how to perform and interpret basic analyses.

What Do We Cover?
  • Non-model-based stratified analyses versus a statistical model: stratified analyses of 2x2xk tables and Mantel-Haenszel estimators
  • Logistic regression for modelling binary outcome variables
  • Continuous outcome variables and linear regression methods: the general linear model
  • Poisson regression for modelling count data, use of offsets
  • Adjusting for potential confounding variables, assessing effect modification and associated statistical inference: hypothesis testing and confidence interval estimation.

Available Software
This course has practical exercises written for: Stata
Note: For practical work participants must bring their own laptop with a fully licensed version of the software.

Extra Information
Related Courses: Introduction to Epidemiological Methods

Course Dates
Next run to be announced

Duration: 2 days
Price: £TBC

Apply Now
(terms and conditions apply)

Return to full course listing
Vertical Divider
  • Home
  • Training
    • Course Registration
    • Terms and Conditions
    • Bespoke Training
    • Mailing List Request
  • Consultancy
    • Expertise
  • Team
    • James Gallagher
    • Sandro Leidi
    • Dankmar Böhning
  • SSC-Stat
  • Resources
  • Contact us
  • Products