7. Randomised Block Design

Introduction to Experimental Design
Training session with Dr Helen Brown, Senior Statistician, at The Roslin Institute, January 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 UA-cam playback settings for the best viewing experience: 1080p HD
************************************************
Content:
Randomised block designs
-Suitable when there is a ‘nuisance’ effect, eg
---Time
---Cage
---Environmental (eg weather)
---Litter
-Nuisance effects
---Not of prime interest
---BUT often cause additional variation in data
---‘Stratify’ across it
‘Randomised block’ design
-Ensure a ‘nuisance factor’ does not influence results
---Eg Day, time of day, cage
-Same structure as ‘two factor’ design
‘Randomised block’ design example
-‘Randomised block’ design example: Test effects of treatment on RBC in mice: Randomised block design
-One fixed factor - Treatment
-Nuisance factor - Week
-RANDOMISE mice to across treatments and weeks
Randomisation using Excel
-Generate random numbers in Excel using =rand() and add column of sequential mouse numbers
-Note: More sophisticated randomisation approaches are also available to allocate weeks and treatments to sequential mice pairs