Genetic Algorithm-Based Bayesian Optimal Design for Network Experiments

Le résumé fourni par la source

We consider the problem of designing an experiment in which experimental units are connected on a network. To find optimal designs for such experiments, the experimental outcomes are assumed to follow a network-outcome model in which units potentially influence one another. To model network interference and correlation, these outcome models are often complex. As a result, the design criteria based on such models depend on unknown parameters and cannot be directly evaluated without making assumptions about their values. We mitigate this problem by defining a Bayesian design criterion, which is the mean squared error of the average treatment effect estimator integrated over a prior distribution for the unknown parameters. In general, this criterion does not have a closed-form formula, and so traditional algorithms to solve for optimal designs cannot be applied. Instead, we propose and study the use of the genetic algorithm to find near-optimal designs. Through extensive numerical studies with various real-life networks and network-outcome models, we demonstrate the robust performance of our method compared to existing design construction strategies.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.