Multistage Estimation of Bounded-Variable Means

TL;DR

This paper introduces a multistage estimation framework for accurately estimating the mean of bounded variables, including binomial parameters, with guaranteed precision and confidence levels.

Contribution

It presents a novel multistage approach that generalizes binomial estimation methods to all bounded variables, establishing fundamental connections and rigorous guarantees.

Findings

Guarantees prescribed levels of precision and confidence

Establishes a fundamental link between binomial parameters and bounded variable means

Provides a generalized multistage estimation methodology

Abstract

In this paper, we develop a multistage approach for estimating the mean of a bounded variable. We first focus on the multistage estimation of a binomial parameter and then generalize the estimation methods to the case of general bounded random variables. A fundamental connection between a binomial parameter and the mean of a bounded variable is established. Our multistage estimation methods rigorously guarantee prescribed levels of precision and confidence.