.. _method-multilevel_blue-group_throttle-best_conditioned: """""""""""""""" best_conditioned """""""""""""""" Throttle multilevel BLUE to only solve for allocations using the groups with the best conditioning in their group covariances **Specification** - *Alias:* None - *Arguments:* None - *JSON argument key:* None **Description** The number of groups in ML BLUE is initially defined using all combinations of the model indices, and group covariances are computed for every group. This throttle then retains a number of groups specified by the provided count, where the retained groups have the highest inverse condition number ("rcond") for their group covariances. This is closely related to :dakkw:`method-multilevel_blue-group_throttle-rcond_tolerance` except that the worst-case group conditioning is not controlled directly. **Examples** .. tab:: Freeform .. code-block:: dakota method model_pointer = 'ENSEMBLE' multilevel_blue pilot_samples = 50 seed = 8674132 group_throttle best_conditioned = 100 max_function_evaluations = 1000 .. tab:: JSON .. code-block:: json { "method": [ { "multilevel_blue": { "model_pointer": "ENSEMBLE", "pilot_samples": {"counts": [50]}, "seed_sequence": [8674132], "group_throttle": {"best_conditioned": 100}, "max_function_evaluations": 1000 } } ] }