Problems in Bayesian analysis of stochastic simulation

ABSTRACT

It is argued that Bayesian methodology is an appropriate tool in certain simulation contexts. Computational problems, specific to simulation applications, are then described in some detail; possible remedies are also outlined.

REFERENCES

• 1: Berber, J.O. (1985)o Statistical Decision Theorb, and Bayesian Analysis. Springer-Verlai~, t~ew York.
• 2: Ethier, S.N. and Kurtz, T.G. (1986). Markov Processes- Characterization and Co~nce. john -~'~l ey, New York.
• 3: Peter W. Glynn, On the role of generalized semi-Markov processes in simulation output analysis, Proceedings of the 15th conference on Winter simulation, p.39-44, December 12-14, 1983, Arlington, Virginia, United States
• 4: Glynn, P.W. (L983). Computational Methods for L~ayesian Simulation. Forthcoming technical report. University of Wisconsin.
• 5: Grassberger, P. and De La Torre, A. (1979). Reggon Field Theory (Schlogle's First ~del) on a Lattice- 14onte Carlo Calculations of Critical Behavior. Ann. Physics 122, 373-396.
• 6: Heyman, D.P. and Sobel, 14.J. (1982). Stochastic ~4odels in Operations Research, Volu~n~e L McGraw- Hill, New York.
• 7: Iglehart, D.L. (1978). The Re:jenerative Method for Simulation Anal~vsis. Trend,.; in Pro~rammjn~ ~|ethodol~, Ill, Software 14odeli~ (ec&ited by K.M. chan3y and R.~Yeli).~ Prentice-~Hal 1, F n~l ewood Cliffs, N.J.
• 8: Ross, S.M. (L980). Introduction to Probabilit~y i4odels. Acade{Ric Press, Ne~ York.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.6 SIMULATION AND MODELING

Additional Classification:
  G. Mathematics of Computing
  G.3 PROBABILITY AND STATISTICS
      Subjects: Stochastic processes

  I. Computing Methodologies
  I.6 SIMULATION AND MODELING

General Terms:
Design, Performance, Theory