Explain Variance Reduction (Antithetic and Control Variates)
Quant ResearchLevel: Foundation
Explain Variance Reduction (Antithetic and Control Variates)
Hints
- What is the estimator and which random variables produce it?
- Separate bias, variance and computational cost; how would you check convergence?
Answer
Antithetic sampling averages payoffs from Z and −Z; it helps at equal computational cost when the paired payoffs are negatively correlated. A control variate uses X−β(Y−E[Y]), with optimal fixed β=Cov(X,Y)/Var(Y). The known control mean is essential. Estimate coefficients on independent pilot data or assess fitting effects, and compute errors using independent pairs or corrected samples. Neither technique guarantees improvement for every payoff or control.
Source and licence: Quantitative Finance: From Mathematical Foundations to Trading Desk Reality — zcoderz · MIT · answer: Quantoros editorial