English

Markov Chain Monte Carlo confidence intervals

Statistics Theory 2016-08-14 v3 Probability Statistics Theory

Abstract

For a reversible and ergodic Markov chain {Xn,n0}\{X_n,n\geq0\} with invariant distribution π\pi, we show that a valid confidence interval for π(h)\pi(h) can be constructed whenever the asymptotic variance σP2(h)\sigma^2_P(h) is finite and positive. We do not impose any additional condition on the convergence rate of the Markov chain. The confidence interval is derived using the so-called fixed-b lag-window estimator of σP2(h)\sigma_P^2(h). We also derive a result that suggests that the proposed confidence interval procedure converges faster than classical confidence interval procedures based on the Gaussian distribution and standard central limit theorems for Markov chains.

Keywords

Cite

@article{arxiv.1209.0703,
  title  = {Markov Chain Monte Carlo confidence intervals},
  author = {Yves F. Atchadé},
  journal= {arXiv preprint arXiv:1209.0703},
  year   = {2016}
}

Comments

Published at http://dx.doi.org/10.3150/15-BEJ712 in the Bernoulli (http://isi.cbs.nl/bernoulli/) by the International Statistical Institute/Bernoulli Society (http://isi.cbs.nl/BS/bshome.htm)

R2 v1 2026-06-21T21:59:39.843Z