Suppose you have a binary randomized controlled experiment designed to measure the causal effect of X on Y. Let the control group be identified by X = 0 and the treatment group by X= 1.

The differences–of–means estimator, denoted by E(Y∣X=1)−E(Y∣X=0), is an estimator of the causal effect of X on Y because the

differences–of–means estimator estimates:

A.

the change in the expectation of Y as result of an observation being in the treatment group as opposed to the control group.

B.

the expectation of Y for observations within the control group.

C.

the expectation of Y for observations within the treatment group.

D.

All of the above.