A Comparison of Methods for Computing Autocorrelation Time

Abstract

This paper describes four methods for estimating autocorrelation time and evaluates these methods with a test set of seven series. Fitting an autoregressive process appears to be the most accurate method of the four. An R package is provided for extending the comparison to more methods and test series.

References in corpus (1)

• Graphical Comparison of MCMC Performance

Cited by in corpus (15)

• Fast Markov chain Monte Carlo sampling for sparse Bayesian inference in high-dimensional inverse problems using L1-type priors
• Neural Density Estimation and Likelihood-free Inference
• ParaDRAM: A Cross-Language Toolbox for Parallel High-Performance Delayed-Rejection Adaptive Metropolis Markov Chain Monte Carlo Simulations
• Investigation of a Multiple-Timescale Turbulence-Transport Coupling Method in the Presence of Random Fluctuations
• Learning interaction kernels in stochastic systems of interacting particles from multiple trajectories
• Graphical Comparison of MCMC Performance
• MatDRAM: A pure-MATLAB Delayed-Rejection Adaptive Metropolis-Hastings Markov Chain Monte Carlo Sampler
• Tempering by Subsampling
• Split Hamiltonian Monte Carlo
• Batch size selection for variance estimators in MCMC
• Monte Carlo sampling in diffusive dynamical systems
• Split HMC for Gaussian Process Models
• Quantifying the Temporal Uncertainties of Nonlinear Turbulence Simulations
• Beyond Application End-Point Results: Quantifying Statistical Robustness of MCMC Accelerators
• Involutive MCMC: a Unifying Framework