All books

Professional

Apps About Coach Log in Start reading

Quantitative Finance · Glossary

What is Burn-in, effective sample size?

Also known as: burn-in · effective sample size

Definition 14.10 Quantitative Methods · Chapter 14 — Bayesian Methods

The burn-in is the initial stretch of a chain discarded because it still depends on the starting point. The effective sample size of nn correlated draws is n/(1+2∑k≥1ρk)n/(1 + 2\sum_{k \ge 1}\rho_k), ρk\rho_k the chain’s autocorrelations: the number of independent draws with the same variance of the mean.

Posterior of the dispersion of the platform’s true Sharpe ratios from the Gibbs sampler (18 000 draws) and from four random-walk Metropolis chains on the marginal posterior, against the empirical-Bayes point estimate 0.41 (dashed). Data: the chapter’s tutorial, seeded.
Figure 14.4. Posterior of the dispersion τ\tau of the platform’s true Sharpe ratios from the Gibbs sampler (18 000 draws) and from four random-walk Metropolis chains on the marginal posterior, against the empirical-Bayes point estimate 0.41 (dashed). Data: the chapter’s tutorial, seeded.
Read in context →