*Geek Box: Block Randomisation

*Geek Box: Block Randomisation

The most basic form of randomising subjects is simple randomization, which involves dividing subjects at random to allocation of either treatment group or control, preferable by using a computer-generated sequence or numbered tables.

The essential characteristic of simple randomisation is that all subjects have an equal chance of allocation to either group. However, subjects may still have differing characteristics that could influence the outcome of interest, like age or sex. To address this, block randomisation divides subjects into multiple, smaller groups of equal subjects based on a predetermined group size.

The advantage of block randomisation is controlling for balance across similar-sized groups, and by stratifying subjects according to similar characteristics to achieve a balance of characteristics between block groups. This allows for particular baseline characteristics, for example age, to be balanced by grouping together particular characteristics which could influence the dependent variable.