Introduction to Analysing Repeated Measures Data
Training session with Dr Helen Brown, Senior Statistician, at The Roslin Institute, March 2016.
************************************************
These training sessions were given to staff and research students at the Roslin Institute. The material is also used for the Animal Biosciences MSc course taught at the Institute.
************************************************
*Recommended YouTube playback settings for the best viewing experience: 1080p HD
************************************************
Content:
Repeated measures: Potential analysis approaches
- Analyse separately at each time point
- Calculate a derived variable from the repeated observations
- Fixed effects model
- Mixed model
Analyse separately at each time point
- Advantages
--- Simplicity
- Disadvantages
--- Multiple testing
--- Problems with interpretation
--- Ignores structure of the data
Analyse a derived variable from the repeated observations
Eg time to maximum, area under curve
- Advantages:
--- Simplicity of analysis
--- Avoidance of multiple testing
- Disadvantage:
--- Missing values may cause problems
Fixed effects model (GLM or ANOVA)
- Complete data
--- Can be satisfactory if treatments compared against correct variation (eg between animal variance)
- Incomplete data
--- Inadequate
General linear model (GLM) or ANOVA if data are complete at each time point
- Eg repeated measurements on crabs of consumption of different diets
- BUT Significance tests for Diet must be based on between crab variation (not residual)
- Some packages offer ‘repeated measures ANOVA’
- Tags
-