Alignment properties in ordinal comparison of discrete event dynamic systems (Q1304056)

Alignment of observed performance orders with true orders is considered and properties of the alignment are investigated. The authors use Spearman's rank correlation coefficient to measure the agreement between the observed and true orders and they show that Spearman's coefficient converges at exponential rates. In the section about simulation planning, they examine the effect of dependence among simulation runs on the alignment probability. Finally, the authors describe applications to the simulation of communication networks, namely, the standard clock technique and they use Spearman's rank correlation coefficient to compare the speed of convergence of the standard clock technique to that of two other methods, i.e., independent simulations and common random numbers.