WSC '95 Proceedings of the 27th conference on Winter simulation
| Hi-index | 0.00 |
When making an inference from a simulation output, the problem we usually encounter is the autocorrelation among observations. In this paper we proposed a technique using regenerative methods to overcome this problem and establish simultaneous confidence intervals for some correlated variables to a prespecified relative precision level. Five simulation models are used to test the performance of this technique and the coverage rate is the criterion. From the empirical results, the performance of this technique is quite satisfactory.