Optimality of Matched-Pair Designs in Randomized Controlled Trials

In randomized controlled trials, treatment is often assigned by stratified randomization. I show that among all randomization schemes treat units with probability one half, a certain matched-pair design achieves the maximum statistical precision for estimating average effect. an important special case, optimal pairs according to baseline outcome. simulation study based on datasets from ten this lowers standard error estimator of effect 10 percent average, and up 34 percent, relative original designs. (JEL C13, C21)