.. _method-importance_sampling-response_levels-compute: """"""" compute """"""" Selection of statistics to compute at each response level .. toctree:: :hidden: :maxdepth: 1 method-importance_sampling-response_levels-compute-probabilities method-importance_sampling-response_levels-compute-gen_reliabilities method-importance_sampling-response_levels-compute-system **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) | Statistic | statistic | `probabilities`__ | Computes probabilities associated with response levels | + + + +--------------------------------+------------------------------------------------------------+ | | | | `gen_reliabilities`__ | Computes generalized reliabilities associated with | | | | | | response levels | +-------------------------+------------------------+--------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `system`__ | Compute system reliability (series or parallel) | +-------------------------+------------------------+--------------------+--------------------------------+------------------------------------------------------------+ .. __: method-importance_sampling-response_levels-compute-probabilities.html __ method-importance_sampling-response_levels-compute-gen_reliabilities.html __ method-importance_sampling-response_levels-compute-system.html **Description** The ``compute`` keyword is used to select which forward stastical mapping is calculated at each response level. *Default Behavior* If ``response_levels`` is not specified, no statistics are computed. If ``response_levels`` is specified but ``compute`` is not, probabilities will be computed by default. If both ``response_levels`` and ``compute`` are specified, then on of the following must be specified: ``probabilities``, ``reliabilities``, or ``gen_reliabilities``. *Expected Output* The type of statistics specified by ``compute`` will be reported for each response level. *Usage Tips* CDF/CCDF probabilities are calculated for specified response levels using a simple binning approach. CDF/CCDF reliabilities are calculated for specified response levels by computing the number of sample standard deviations separating the sample mean from the response level. **Examples** .. tab:: Freeform .. code-block:: dakota method sampling sample_type random samples = 100 seed = 1 complementary distribution response_levels = 3.6e+11 4.0e+11 4.4e+11 6.0e+04 6.5e+04 7.0e+04 3.5e+05 4.0e+05 4.5e+05 compute reliabilities .. tab:: JSON .. code-block:: json { "method": [ { "sampling": { "sample_type": {"random": true}, "samples": 100, "seed": 1, "distribution": {"complementary": true}, "response_levels": {"values": [3.6e+11, 4.0e+11, 4.4e+11, 6.0e+04, 6.5e+04, 7.0e+04, 3.5e+05, 4.0e+05, 4.5e+05]}, "compute": {"reliabilities": true} } } ] }