calibrate_error_multipliers

Calibrate hyper-parameter multipliers on the observation error covariance

Specification

  • Alias: None

  • Arguments: None

  • JSON argument key: None

Child Keywords:

Required/Optional

Description of Group

JSON Group Key

Dakota Keyword

Dakota Keyword Description

Required (Choose One)

Selection

selection

one

Calibrate one hyper-parameter multiplier across all responses/experiments

per_experiment

Calibrate one hyper-parameter multiplier per experiment

per_response

Calibrate one hyper-parameter multiplier per response

both

Calibrate one hyper-parameter multiplier for each response/experiment pair

Optional

hyperprior_parameters

Specify shape (alpha) and scale (beta) of the inverse gamma hyper-parameter prior

Description

Calibrate one or more multipliers on the user-provided observation error covariance ( experiment_variance_type). Options include one multiplier on the whole block-diagonal covariance structure, one multiplier per_experiment covariance block, one multiplier per_response covariance block, or separate multipliers for each response/experiment pair (for a total of number experiments X number response groups).

Default Behavior: No hyper-parameter calibration. When hyper-parameter calibration is enabled, the default prior on the multiplier is a diffuse inverse gamma, with mean and mode approximately 1.0.

Expected Output: Final calibration results will include both inference parameters and one or more calibrated hyper-parameters.

Usage Tips: The per_response option can be useful when each response has its own measurement error process, but all experiments were gathered with the same equipment and conditions. The per_experiment option might be used when working with data from multiple independent laboratories.

Examples

Perform Bayesian calibration with 2 calibration variables and two hyper-parameter multipliers, one per each of two responses. The multipliers are assumed the same across the 10 experiments. The priors on the multipliers are specified using the hyperprior_alphas and hyperprior_betas keywords.

method
  bayes_calibration queso
    chain_samples = 1000 seed = 348
    dram
    calibrate_error_multipliers per_response
      hyperprior_alphas = 27.0
      hyperprior_betas  = 26.0

variables
  uniform_uncertain 2
    upper_bounds  1.e8 10.0
    lower_bounds  1.e6 0.1
    initial_point 2.85e7 2.5
    descriptors   'E' 'w'

responses
  calibration_terms = 2
    calibration_data_file = 'expdata.withsigma.dat'
      freeform
      num_experiments = 10
      experiment_variance_type = 'scalar'
    no_gradients
    no_hessians
{
  "method": [
    {
      "bayes_calibration": {
        "calibrate_error_multipliers": {
          "selection": {
            "per_response": true
          },
          "hyperprior_parameters": {
            "alphas": [27.0],
            "betas": [26.0]
          }
        },
        "sub_method": {
          "queso": {
            "chain_samples": 1000,
            "seed": 348,
            "mcmc_algorithm": {
              "dram": true
            }
          }
        }
      }
    }
  ],
  "variables": [
    {
      "uniform_uncertain": {
        "count": 2,
        "upper_bounds": [100000000.0, 10.0],
        "lower_bounds": [1000000.0, 0.1],
        "initial_point": [28500000.0, 2.5],
        "descriptors": ["E", "w"]
      }
    }
  ],
  "responses": [
    {
      "response_type": {
        "calibration_terms": {
          "count": 2,
          "data_specification": {
            "calibration_data_file": {
              "filename": "expdata.withsigma.dat",
              "format": {
                "freeform": true
              },
              "num_experiments": 10,
              "experiment_variance_type": ["scalar"]
            }
          }
        }
      },
      "gradient_type": {
        "no_gradients": true
      },
      "hessian_type": {
        "no_hessians": true
      }
    }
  ]
}