Probability-Based Estimation

We develop a theory of estimation when in addition to a sample of $n$ observed outcomes the underlying probabilities of the observed outcomes are known, as is typically the case in the context of numerical simulation modeling, e.g. in epidemiology. For this enriched information framework, we design unbiased and consistent ``probability-based'' estimators whose variance vanish exponentially fast as $n\to\infty$, as compared to the power-law decline of classical estimators' variance.