 Control variates

A control variate is a random variable with known expected value whose centered value is subtracted from a Monte Carlo estimator to reduce its variance. For a mean-zero vector $G$, put $S=\mathrm{Cov}(G)$ and $c=\mathrm{Cov}(G,H)$. When $S$ is invertible, the optimal estimator averages $H-c^T{S}^{-1}G$ and has variance $(\mathrm{Var}(H)-c^T{S}^{-1}c)/N$ for $N$ independent draws. Improvement is strict exactly when $c\ne 0$.

Control variates are a statistical technique used to reduce the variance of an estimator in Monte Carlo simulations and other contexts. The idea is to leverage the known properties of another random variable that is correlated with the variable of interest to improve the estimation accuracy. ### Key Concepts: 1. **Random Variable of Interest**: Let \(X\) be the random variable you want to estimate.