Mohamed Azab and Mohammed Moanes Ezzaldean Ali two algebraic
derivative estimators run simultaneously, but in an overlapping fashion, so as to obtain valid results at all times except for the very first small-interval. The reinitialization of each identifier is separated by a time interval of duration T=2. This can be performed by defining two time lines, t1 and t2, which are defined
as follows: t1 = t mod T and t2 = (t - T/2) mod T.
This policy is called a switched overlapping estimator technique. Figure 1 depicts the time lines for both identifiers.
Some ranking and selection (R&S) procedures for steady- state simulation require an estimate of the asymptotic variance parameter of each system to guarantee a certain probability of correct selection. We show that the performance of such R&S procedures depends on the quality of the variance estimates that are used.