Medicine and Health Sciences Commons^™

Addressing Parameter Uncertainty In Sd Models With Fit-To-History And Monte-Carlo Sensitivity Methods, Wayne Wakeland, Jack Homer

Systems Science Faculty Publications and Presentations

We present a practical guide, including a step-by-step flowchart, for establishing uncertainty intervals for key model outcomes in the face of uncertain parameters. The process starts with Powell optimization (e.g., using VensimTM) to find a set of uncertain parameters (the “optimum” parameter set or OPS) that minimize the model fitness error relative to available reference behavior data. The optimization process also helps in refinement of assumed parameter uncertainty ranges. Next, Markov Chain Monte Carlo (MCMC) or conventional Monte Carlo (MC) randomization is used to create a sample of parameter sets that fit the reference behavior data nearly as well as …