Using path control variates in activity network simulation
WSC '85 Proceedings of the 17th conference on Winter simulation
Hi-index | 0.00 |
When control variates are applied to a simulation with multiple responses some of the potential effeciency improvement is lost if the optimal control coefficients must be estimated. To quantify this phenomenon, we formulate a variance ratio and a loss factor that are substantially simpler than the corresponding efficiency measures developed recently by Rubinstein and Marcus [12].