Replication splitting and variance for simulating discrete-parameter stochastic processes
Operations Research Letters
Hi-index | 0.00 |
Consider the problem of estimating the mean of a strictly stationary stochastic process by Monte Carlo sampling for the case in which the process has autocorrelation function {@a^|^s^|, |@a| 1 and t^*=1, n^* and t^*1, and n^*1. Results are presented in terms of @a and @q, a relative cost ratio. Also, we extend the analysis to autocorrelation functions that are convex combinations of geometrically decreasing quantities.