Russell R. Barton | Searcharxiv

arXiv2022

Stochastic Simulation Uncertainty Analysis to Accelerate Flexible Biomanufacturing Process Development

Motivated by critical challenges and needs from biopharmaceuticals manufacturing, we propose a general metamodel-assisted stochastic simulation uncertainty analysis framework to accelerate the development of a simulation model with modular design for flexible production processes. There are often very limited process observations. Thus, there exist both simulation and model uncertainties in the system performance estimates. In biopharmaceutical manufacturing, model uncertainty often dominates. The proposed framework can produce a confidence interval that accounts for simulation and model uncertainties by using a metamodel-assisted bootstrapping approach. Furthermore, a variance decomposition is utilized to estimate the relative contributions from each source of model uncertainty, as well as simulation uncertainty. This information can be used to improve the system mean performance estimation. Asymptotic analysis provides theoretical support for our approach, while the empirical study demonstrates that it has good finite-sample performance.

stat.ME↗

arXiv2020

Statistical Uncertainty Analysis for Stochastic Simulation

When we use simulation to evaluate the performance of a stochastic system, the simulation often contains input distributions estimated from real-world data; therefore, there is both simulation and input uncertainty in the performance estimates. Ignoring either source of uncertainty underestimates the overall statistical error. Simulation uncertainty can be reduced by additional computation (e.g., more replications). Input uncertainty can be reduced by collecting more real-world data, when feasible. This paper proposes an approach to quantify overall statistical uncertainty when the simulation is driven by independent parametric input distributions; specifically, we produce a confidence interval that accounts for both simulation and input uncertainty by using a metamodel-assisted bootstrapping approach. The input uncertainty is measured via bootstrapping, an equation-based stochastic kriging metamodel propagates the input uncertainty to the output mean, and both simulation and metamodel uncertainty are derived using properties of the metamodel. A variance decomposition is proposed to estimate the relative contribution of input to overall uncertainty; this information indicates whether the overall uncertainty can be significantly reduced through additional simulation alone. Asymptotic analysis provides theoretical support for our approach, while an empirical study demonstrates that it has good finite-sample performance.

stat.ME↗