values

Specifies matrix values to use as the MCMC proposal covariance.

Specification

  • Alias: None

  • Arguments: REAL ARRAY

  • JSON argument key: elements

Child Keywords:

Required/Optional

Description of Group

JSON Group Key

Dakota Keyword

Dakota Keyword Description

Required (Choose One)

Covariance Form

covariance_form

diagonal

Specifies the diagonal matrix format when specifying a user-specified proposal covariance.

matrix

Specifies the full matrix format when specifying a user-specified proposal covariance.

Description

This keyword selection results in definition of the MCMC proposal covariance from user-specified matrix values. The matrix input format must be declared as either a full matrix or a matrix diagonal.

Default Behavior

This option is not the default, and generally implies special a priori knowledge from the user.

Usage Tips

This option is not supported for the case of transformations to standardized probability space.

Examples

method,
        bayes_calibration queso
         samples = 1000 seed = 348
          dram
          proposal_covariance
            values ... # See leaf nodes for required format option
{
  "method": [
    {
      "bayes_calibration": {
        "queso": {
          "samples": 1000,
          "seed": 348,
          "dram": {},
          "proposal_covariance": {
            "values": {}
          }
        }
      }
    }
  ]
}