Comparing like with like is a key feature of fair tests of treatments.
Random allocation, or some other unbiased way of determining who receives which treatment in a study, is used to ensure that comparison groups are as similar as possible at the beginning of a study.
In studies where participants decide themselves which treatment they are allocated, there is a high risk of bias due to the likelihood of there being differences between the [treatment comparison groups (confounders)|treatment comparison group] other than the treatments being compared.
allocation bias · allocation schedule · random allocation · stratified randomization
If you feel that this definition hasn't helped you to understand the term, click on our monkey to let us know.