Adaptive Markov chain Monte Carlo;
kernel estimators of asymptotic variance;
CONSISTENCY;
ERGODICITY;
HETEROSKEDASTICITY;
D O I:
10.1214/10-AOS828
中图分类号:
O21 [概率论与数理统计];
C8 [统计学];
学科分类号:
020208 ;
070103 ;
0714 ;
摘要:
We study the asymptotic behavior of kernel estimators of asymptotic variances (or long-run variances) for a class of adaptive Markov chains. The convergence is studied both in L-P and almost surely. The results also apply to Markov chains and improve on the existing literature by imposing weaker conditions. We illustrate the results with applications to the GARCH(1, 1) Markov model and to an adaptive MCMC algorithm for Bayesian logistic regression.
机构:
Univ Cambridge, Dept Pure Math & Math Stat, Cambridge, EnglandUniv Cambridge, Computat & Biol Learning Lab, Cambridge, England
Rowland, M.
Gretton, A.
论文数: 0引用数: 0
h-index: 0
机构:
UCL, Gatsby Computat Neurosci Unit, London, EnglandUniv Cambridge, Computat & Biol Learning Lab, Cambridge, England
Gretton, A.
Ghahramani, Z.
论文数: 0引用数: 0
h-index: 0
机构:
Univ Cambridge, Computat & Biol Learning Lab, Cambridge, England
Uber AI Labs, San Francisco, CA USAUniv Cambridge, Computat & Biol Learning Lab, Cambridge, England