Techniques for Efficient Monte Carlo Simulation. Volume 3. Variance Reduction

Abstract : Many Monte Carlo simulation problems lend themselves readily to the application of variance reduction techniques. These techniques can result in great improvements in simulation efficiency. The document describes the basic concepts of variance reduction (Part 1), and a methodology for application of variance reduction techniques is presented in Part 2. Appendices include the basic analytical expressions for application of variance reduction schemes as well as an abstracted bibliography. The techniques considered here include importance sampling, Russian roulette and splitting, systematic sampling, stratified sampling, expected values, statistical estimation, correlated sampling, history reanalysis, control variates, antithetic variates, regression, sequantial sampling, adjoint formulation, transformations, orthonormal and conditional Monte Carlo. Emphasis has been placed on presentation of the material for application by the general user. This has been accomplished by presenting a step by step procedure for selection and application of the appropriate technique(s) for a given problem.

[1]  H. Kahn,et al.  Methods of Reducing Sample Size in Monte Carlo Computations , 1953, Oper. Res..

[2]  M. Kalos.  Monte Carlo Integration of the Adjoint Gamma-Ray Transport Equation , 1968 .

[3]  I. G. Nidekker,et al.  Selected applications of non-linear programming: J. Bracken and G. P. McCormick, John Wiley, New York — London — Sydney — Toronto. XII + 110 pp., 84 sh. 1968☆ , 1969 .

[4]  Van Slyke,et al.  MONTE CARLO METHODS AND THE PERT PROBLEM , 1963 .

[5]  George S. Fishman.  The Allocation of Computer Time in Comparing Simulation Experiments , 1968, Oper. Res..

[6]  Variance reduction in the Monte Carlo method for determing the volume of multidimensional non analytic solids , 1967 .

[7]  S. Ehrenfeld,et al.  The Efficiency of Statistical Simulation Procedures , 1962 .

[8]  E. S. Page,et al.  On Monte Carlo Methods in Congestion Problems: II. Simulation of Queuing Systems , 1965 .

[9]  Y. A. Schreider.  The monte carlo method , 1966 .

[10]  F. H. Clark.  THE EXPONENTIAL TRANSFORM AS AN IMPORTANCE-SAMPLING DEVICE. A REVIEW , 1966 .

[11]  John M. Burt,et al.  Conditional Monte Carlo: A Simulation Technique for Stochastic Network Analysis , 1971 .

[12]  C. E. Clark.  Importance Sampling in Monte Carlo Analyses , 1961 .

[13]  J. C. Koop.  On Splitting a Systematic Sample for Variance Estimation , 1971 .

[14]  Jack Moshman,et al.  The Application of Sequential Estimation to Computer Simulation and Monte Carlo Procedures , 1958, JACM.

[15]  E. L. Pugh.  A Gradient Technique of Adaptive Monte Carlo , 1966 .

[16]  Daniel A. Relles.  Variance Reduction Techniques for Monte Carlo Sampling from Student Distributions , 1970 .

[17]  Jerome Spanier,et al.  An Analytic Approach to Variance Reduction , 1970 .

[18]  R. Serfling.  Approximately Optimal Stratification , 1968 .

[19]  M. Degroot,et al.  Optimal Two-Stage Stratified Sampling , 1969 .

[20]  V. R. Cain,et al.  Adjoint and Importance in Monte Carlo Application , 1967 .

[21]  C. Särndal.  The Use of a Stratification Variable in Estimation by Proportional Stratified Sampling , 1968 .

[22]  H. Kahn.  APPLICATIONS OF MONTE CARLO , 1954 .