metropolis_hastings
Use the Metropolis-Hastings MCMC algorithm
Topics
bayesian_calibration
Specification
Alias: None
Arguments: None
Default: dram
Description
This keyword specifies the use of a Metropolis-Hastings algorithm for the MCMC chain generation. This means there is no delayed rejection and no adaptive proposal covariance updating as in DRAM.
Default Behavior
Five MCMC algorithm variants are supported currently in QUESO: dram
,
delayed_rejection
, adaptive_metropolis
, metropolis_hastings
, and
multilevel
. The default is dram
.
Four MCMC algorithm variants are currently supported in MUQ: dram
,
delayed_rejection
, metropolis_hastings
and adaptive_metropolis
.
Usage Tips
If the user wants to use Metropolis-Hastings, possibly as a comparison to the other methods which involve more chain adaptation, this is the MCMC type to use.
Examples
method,
bayes_calibration queso
metropolis_hastings
samples = 10000 seed = 348