dram

Use the DRAM MCMC algorithm

Topics

bayesian_calibration

Specification

  • Alias: None

  • Arguments: None

  • Default: dram

Child Keywords:

Required/Optional

Description of Group

Dakota Keyword

Dakota Keyword Description

Optional

num_stages

Number of stages

Optional

scale_type

Type of scaling to use

Optional

delay_scale

Scaling parameter

Optional

period_num_steps

Number of steps between updates of the proposal covariance

Optional

starting_step

Number of steps prior to start of proposal covariance adaptation

Optional

adapt_scale

Sample covariance scaling used to define proposal covariance

Description

The type of Markov Chain Monte Carlo used. This keyword specifies the use of DRAM, (Delayed Rejection Adaptive Metropolis) [HLMS06].

Default Behavior

Five MCMC algorithm variants are supported: dram, delayed_rejection, adaptive_metropolis, metropolis_hastings, and multilevel. The default is dram.

Usage Tips

If the user knows very little about the proposal covariance, using dram is a recommended strategy. The proposal covariance is adaptively updated, and the delayed rejection may help improve low acceptance rates.

Examples

method,
        bayes_calibration queso
          dram
          samples = 10000 seed = 348