2. What is Randomisation?

2.1. Randomisation using Stratification

Normally participants would be allocated to a treatment group randomly, and while this maintains a good overall balance, it can lead to imbalances within sub-groups. For example if a majority of the participants who were receiving the medicine happened to be male, or smokers, the statistical value of the study would be reduced.

The traditional method to avoid this problem is to stratify participants according to a number of factors (e.g. age or smokers and non-smokers) and to use a separate randomisation list for each group. Each randomisation list would be created such that after every block of a number of participants, there would be an equal number in each treatment group.

A stratification factor can either be:
  • A categorical covariate - for example: sex, 2 levels, female, male.
  • A discretised continuous covariate (i.e. continuous information which has been split into discrete ranges) - for example: age, 3 levels, less than 40 years, 40 to 59, 60 years plus.
Example: randomisation list with stratification by one lifestyle factor: smoker - non-smoker

Smokers

Non-smokers

Participant No

Random arm/group

Participant No

Random arm/group

001

A

003

B

002

B

005

A

004

B

006

B