Stratified filtered sampling in stochastic optimization

Abstract

We develop a methodology for evaluating a decision strategy generated by a stochastic optimization model. The methodology is based on a pilot study in which we estimate the distribution of performance associated with the strategy, and define an appropriate stratified sampling plan. An algorithm we call filtered search allows us to implement this plan efficiently. We demonstrate the approach's advantages with a problem in asset / liability management for an insurance company.

Distributed computing approaches for large‐scale probit‐based stochastic user equilibrium problems

“…Such a sampling technique is called as simple random sampling . Note that the accuracy of the Monte Carlo simulation can be further improved if some advanced sampling techniques are used, for instance, stratified sampling, importance sampling, antithetic sampling (see, ). Therefore, if an accuracy level is predetermined, these sampling techniques would reduce the sample size required and hence further reduce the execution time.…”

Sampling strategies

“…e.g. applied mathematics [56], software testing [80], biological sciences [54], optimization [89], Monte Carlo quadrature [44], etc.…”

Stochastic Optimization of the Highland Lakes System in Texas

“…Some time was spent considering representing scenarios with string structures rather than a scenario tree. Recent investigations have found that using a string form to represent scenarios can have advantages over tree structures (Rush et al 2000), although ensuring nonanticipativity may present special challenges with the Highland Lakes model. Since current versions of SPIGOT do not automatically generate scenarios in tree form, there are additional logistical and practical reasons for considering the use of scenario strings.…”