Introduction to Linear Mixed Models using Stata

Overview
Mixed modelling is a modern and powerful data analysis tool for modelling clustered data, typically used for modelling data collected in trials where the levels of a factor are considered to be a random selection from a wider pool, or in the presence of a multi-level structure with different levels of variability.  Such models offer potential benefits such as: the ability to cope with modelling complex data structures, greater generalisability of results, accommodation of missing values and the possibility of increasing the precision of treatment comparisons.  In particular, mixed models have been extensively used to analyse repeated measurements where, for example, measurements taken over time in a clinical trial naturally cluster according to patient.  In general, the course will focus on medical and health related applications of mixed modelling.  Specific applications include multi-centre trials and cross-over trials in addition to the analysis of repeated measurements.
The course focuses on the linear mixed model, assuming normally distributed data, and on how to fit linear mixed models and interpret the results for a range of common medical and health related applications.  Only essential theoretical aspects of mixed models will be summarised.  The Stata software will be used for practical work and to illustrate analyses in presentations.

Who Should Attend?
Data analysts and statisticians working in medicine, health and related areas, who wish to have a practical introduction to linear mixed models.  It will be assumed that participants are Stata users and are familiar with the practical use of linear models, covering regression models and ANOVA.

How You Will Benefit
The course will give you the skills to formulate, fit and interpret mixed models for a range of practical situations, as well as an appreciation of some of the benefits of mixed modelling.

What Do We Cover?
  • Concept of fixed versus random effects
  • Simple random effects and variance components models for modelling clustered data
  • A summary of the important theoretical aspects of mixed models: maximum likelihood versus REML for fitting mixed models, estimating and testing fixed effects, degrees of freedom options and the Kenward-Roger method
  • Model checking
  • Multilevel modelling for hierarchical data structures
  • Multi-centre analyses
  • Mixed models for cross-over designs
  • Repeated measurements analysis: random coefficient and marginal models
  • Practical experience, fitting models and interpreting Stata output
  • Convergence issues
  • Stata's -mixed- command.

Software
Practical work may be done in: 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 Generalised Linear Mixed Models using Stata; Introduction to Linear Mixed Models using R; Linear Mixed Models; Generalised Linear Mixed Models
Course Dates
Next run to be announced

Duration: 2 days
Price: £TBC

Apply Now
(terms and conditions apply)

Return to full course listing