Integrated Variance Reduction Strategies for Simulation

@article{Avramidis1996IntegratedVR,
  title={Integrated Variance Reduction Strategies for Simulation},
  author={Athanassios N. Avramidis and James R. Wilson},
  journal={Oper. Res.},
  year={1996},
  volume={44},
  pages={327-346}
}
We develop strategies for integrated use of certain well-known variance reduction techniques to estimate a mean response in a finite-horizon simulation experiment. The building blocks for these integrated variance reduction strategies are the techniques of conditional expectation, correlation induction including antithetic variates and Latin hypercube sampling, and control variates; all pairings of these techniques are examined. For each integrated strategy, we establish sufficient conditions… 

Figures and Tables from this paper

Variance reduction techniques: Experimental comparison and analysis for single systems

TLDR
It is observed that a variance reduction cannot be guaranteed for every instance a VRT is applied, and that the less-sophisticated techniques often perform better than the relatively more-complex techniques (LHS, PS).

Combined variance reduction techniques in fully sequential selection procedures

TLDR
This paper investigates combining various variance reduction techniques into the fully sequential framework, resulting in different R&S procedures with either finite-time or asymptotic statistical validity.

Correlation-induction techniques for estimating quantiles in simulation experiments

TLDR
A central limit theorem is established for the single-sample estimator based on Latin hypercube sampling, showing that asymptotically this estimator is unbiased and has smaller variance than the comparable direct-simulation estimators based on independent replications.

Combination of General Antithetic Transformations and Control Variables

TLDR
This paper provides conditions under which it can formally prove that the variance is minimized by choosing equal weights and equal control variate coefficients across the different points of evaluation, regardless of the function (integrand) that is evaluated.

Assessing the Efficiency of Variance Reduction Methods in the Construction Project Network Simulation

The Monte Carlo simulation has become a standard tool in the practice of planning risk-affected projects. In particular, it is frequently applied to testing the impact of risk on schedule networks

A new variance reduction method for option pricing based on sampling the vertices of a simplex

In option pricing based on the Monte Carlo method (MC) (see Boyle (1976)), various techniques for variance reduction are used for computational efficiency. Boyle et al. (1997) summarizes variance

Recent Advances in Randomized Quasi-Monte Carlo Methods

TLDR
The main focus is the applicability of quasi-Monte Carlo (QMC) methods to practical problems that involve the estimation of a high-dimensional integral and how this methodology can be coupled with clever transformations of the integrand in order to reduce the variance further.

Variance Reduction via Lattice Rules

This is a review article on lattice methods for multiple integration over the unit hypercube, with a variance-reduction viewpoint. It also contains some new results and ideas. The aim is to examine

Efficiency improvement and variance reduction

  • P. L’Ecuyer
  • Mathematics
    Proceedings of Winter Simulation Conference
  • 1994
TLDR
Methods such as common random numbers, antithetic variate, control variates, importance sampling, conditional Monte Carlo, stratified sampling, and some others are discussed, as well as the combination of certain of those methods.

Five-stage procedure for the evaluation of simulation models through statistical techniques

  • J. Kleijnen
  • Economics
    Proceedings Winter Simulation Conference
  • 1996
TLDR
This paper recommends the following sequence for the evaluation of simulation models: screening, validation, optimization, uncertainty analysis, and optimization.
...

References

SHOWING 1-10 OF 46 REFERENCES

A Central Limit Theorem for Latin Hypercube Sampling

SUMMARY Latin hypercube sampling (LHS) is a technique for Monte Carlo integration, due to McKay, Conover and Beckman. M. Stein proved that LHS integrals have smaller variance than independent and

Estimating simulation metamodels using combined correlation-based variance reduction techniques

This paper develops a procedure for jointly applying all of the correlation-based variance reduction techniques (namely, die methods of antithetic variates, common random numbers, and control

Antithetic Variates, Common Random Numbers and Optimal Computer Time Allocation in Simulation

TLDR
Two simple variance reduction techniques are discussed, viz. antithetic variates and common random numbers, and a procedure is derived that starts with some pilot runs for both systems and estimates which alternative minimizes the variance.

Control Variate Remedies

TLDR
An evaluation of the small-sample statistical properties of the proposed remedies for violations of the rich theory of control variates, including jackknifing and splitting, is presented.

Large sample properties of simulations using latin hypercube sampling

Latin hypercube sampling (McKay, Conover, and Beckman 1979) is a method of sampling that can be used to produce input values for estimation of expectations of functions of output variables. The

Efficiency improvement and variance reduction

  • P. L’Ecuyer
  • Mathematics
    Proceedings of Winter Simulation Conference
  • 1994
TLDR
Methods such as common random numbers, antithetic variate, control variates, importance sampling, conditional Monte Carlo, stratified sampling, and some others are discussed, as well as the combination of certain of those methods.

Strategies for combining antithetic variates and control variates in designed simulation experiments

In this paper we examine three methods for combining the variance reduction techniques of antithetic variates and control variates to estimate the mean response in a designed simulation experiment.

A Comparison Of Variance Reducing Techniques In Pert Simulations

TLDR
This paper investigates the simultaneous application of variance-reduction techniques to increase the efficiency of PERT simulations with three project networks of varying complexity combined two by two to simulate the completion times.

Estimation of multiresponse simulation metamodels using control variates

This paper provides a unified development of the method of control variates for simulation experiments in which the objective is estimation of a multiresponse metamodel---that is, a linear model for

Validation of Simulation Analysis Methods for the Schruben-Margolin Correlation-Induction Strategy

TLDR
To handle simulation experiments that display significant departures from the Schruben-Margolin covariance structure, this paper presents alternative versions of the goodness-of-fit test and the follow-up analysis for the postulated metamodel that merely requires jointly normal responses.