Randomising your participants can be quite straightforward once you know how. The main thing you need is a list of participants in a spreadsheet (either Excel or Google Sheets). You can use our randomisation guides (links below) to turn this into a randomised list.
In a simple trial, there are usually two groups: the intervention group exposed to your new policy, and the control group that gets the business-as-usual policy. However, there can be many more groups in complex trials testing out different changes against one another.
How to randomise
You can randomise a list of participants in three simple steps:
- Generate a random number for each participant
- Sort the random numbers in numerical order
- Categorise your list into control and intervention groups
We have produced two short guides to walk you through this process. You can download them below. Begin with the Word guide to explain the process, and then practice using the Excel guide:
You can also watch the short video below, which walks you through how to do it.
Randomisation walkthrough video
What to randomise?
At the beginning of your trial you need to decide the unit of randomisation. In the case of a trial looking at take-up rates of childcare within a local area, individual randomisation – randomising parents or carers to receive either the intervention or business-as-usual – is probably the most appropriate way to do it. But other trials will be different. For example, you could conduct a trial where children’s centres are the unit of randomisation; some children’s centres deliver a new intervention and some continue to deliver ‘business as usual’.
