Abstract
The method of antithetic variates is a well known technique for reducing the variability of estimators in computer simulation experiments. It is shown that in many, if not most simulations, the usually suggested way of applying the method suffers from two weaknesses. One is so serious that it can lead to estimators which are worse than if the technique is not used at all. Simple alternatives are suggested which do not suffer either weakness. A numerical example is given illustrating the advantages of these alternative procedures.