Guaranteed Monte Carlo Methods for Bernoulli Random Variables

TL;DR

This paper introduces a MATLAB algorithm that guarantees accurate estimation of Bernoulli probabilities within a specified error margin and confidence level using Hoeffding's inequality, enhancing Monte Carlo methods.

Contribution

It presents a new algorithm that automatically determines the sample size needed for accurate Bernoulli probability estimation with guaranteed confidence.

Findings

Algorithm guarantees estimation within error tolerance

Uses Hoeffding's inequality for confidence bounds

Implemented in MATLAB as part of GAIL

Abstract

Simple Monte Carlo is a versatile computational method with a convergence rate of $O(n^{-1/2})$. It can be used to estimate the means of random variables whose distributions are unknown. Bernoulli random variables, $Y$, are widely used to model success (failure) of complex systems. Here $Y=1$ denotes a success (failure), and $p=\mathbb{E}(Y)$ denotes the probability of that success (failure). Another application of Bernoulli random variables is $Y=\mathbb{1}_{R}(\boldsymbol{X})$, where then $p$ is the probability of $\boldsymbol{X}$ lying in the region $R$. This article explores how estimate $p$ to a prescribed absolute error tolerance, $\varepsilon$, with a high level of confidence, $1-\alpha$. The proposed algorithm automatically determines the number of samples of $Y$ needed to reach the prescribed error tolerance with the specified confidence level by using Hoeffding's inequality. The algorithm described here has been implemented in MATLAB and is part of the Guaranteed Automatic Integration Library (GAIL).