Dakota Reference Manual  Version 6.4
Large-Scale Engineering Optimization and Uncertainty Analysis
 All Pages
prior


Uses the covariance of the prior distributions to define the MCMC proposal covariance.

Topics

This keyword is related to the topics:

Specification

Alias: none

Argument(s): none

Description

This keyword selection results in definition of the MCMC proposal covariance from the covariance of the prior distributions. This covariance is currently assumed to be diagonal without correlation.

Default Behavior

This is the default proposal_covariance option.

Usage Tips

Since this proposal covariance is defined globally, the chain does not need to be periodically restarted using local updates to this proposal. However, it is usually effective to adapt the proposal using one of the adaptive metropolis MCMC options.

Examples

method,
        bayes_calibration queso
          samples = 2000 seed = 348
          dram
          proposal_covariance prior