*No-one does this but the idea was to introduce the idea of conditional exchangeability
This balancing is most frequently done by stratification.
bmj.com/content/345/bm…
Take a categorical covariate. For a pair (or 'block') of people with a given value of that covariate, one will be assigned to control arm and the other to research arm.
For the first, P(Z=1)=0.5
For the second, P(Z=1)=0 or 1, depending on what the first person got. Note that this probability was caused by their covariate value X.
But do read on, things are about to look up.
Thoughts?