Critical estimation issues are the size of the sample to be collected and the independence of observations used to compute statistics, particularly confidence intervals. Replication statistics provide the data for computing point estimates and confidence intervals for system parameters of interest (see Section 3.10).
In particular, we seek to minimize the number of replications and their length, and still obtain reliable statistics. A good design of simulation replications allows the analyst to obtain the most statistical information from simulation runs for the least computational cost. The main issues addressed by output analysis follow: It provides the main value-added of the simulation enterprise by trying to understand system behavior and generate predictions for it. Thus, as its name suggests, output analysis focuses on the analysis of simulation results (output statistics). Output analysis is the modeling stage concerned with designing replications, computing statistics from them and presenting them in textual or graphical format.
Each run of the simulation program, called a replication in simulation parlance, produces a sample system history from which various statistics are estimated via output analysis. Rather, we develop a simulation program that encapsulates that probability law by scheduling and processing random events. Except for very simple cases rarely encountered in practice, that law is too complicated to write down, and consequently, we cannot analytically derive system statistics either. Recall that a Monte Carlo model is governed by a probability law that determines its random behavior.
0 kommentar(er)
