Title :
Sequential Bayesian analysis of simulation experiments
Author :
Haddock, Jorge ; Willemain, Thomas R.
Author_Institution :
Dept. of Decision Sci. & Eng. Syst., Rensselaer Polytech. Inst., Troy, NY, USA
Abstract :
Prior information is incorporated in the analysis of simulation experiments to reduce the number of observations needed to estimate delay before service in a queuing system with a specified precision. The research extends to simulation of queuing systems a previous successful application of sequential Bayesian analysis to interrupted time series experiments. The results include methodologies that use sequential Bayesian methods for analyzing batch means as well as observations of individual entities within a single simulation run
Keywords :
Bayes methods; discrete event simulation; queueing theory; statistical analysis; time series; interrupted time series experiments; prior information; queuing systems; sequential Bayesian analysis; simulation experiments; Analytical models; Bayesian methods; Computational modeling; Delay estimation; Information analysis; Phase estimation; Queueing analysis; Sequential analysis; Systems engineering and theory; Time series analysis;
Conference_Titel :
Simulation Conference, 1990. Proceedings., Winter
Conference_Location :
New Orleans, LA
Print_ISBN :
0-911801-72-3
DOI :
10.1109/WSC.1990.129527
