On simulating arbitrary events
Tóm tắt
In simulation studies, the distributional properties of random variables associated witharbitrary events in point processes, queues, and other stochastic models are to be understood as appropriate averages over long simulation runs. We caution against trying to generate arbitrary events explicitly by some randomized selection. Because of the likelihood of hidden selection biases, that easily results in significant errors. The point is illustrated by an example for which explicit formulas yield computational results that allow comparisons with the simulation estimates.
Tài liệu tham khảo
Bertrand J. (1907).Calcul des probabilités. Gauthier-Villars; 2nd edition, 1907, Reprinted, 1972; Chelsea.
Daley D.J., Vere-Jones D. and Smirnov B. M. (2002).An Introduction to the Theory of Point Processes. Springer Verlag, 2nd edition.
Franken P., König D., Arndt U. and Schmidt V. (1983).Queues and Point Processes. John Wiley.
Karr A.F. (1991).Point Processes and Their Statistical Inference. Marcel Dekker.
Neuts M.F., Guo J., Zukerman, M. and Vu H.L. (2003). The Waiting Time Distribution for a TDMA Model with a Finite Buffer. Proceedings of INFOCOM 2003, San Francisco, April 2003.