nnpiv.diagnostics.relative_wellposedness_effective_from_data

nnpiv.diagnostics.relative_wellposedness_effective_from_data(data, *, e_g, A, B=None, C, C_prime, mask_s=None, mask_t=None, **kwargs)

Run the post-estimation kappa_eff diagnostic from dataset selectors.

Parameters

• data (DataFrame, mapping, or 2D array-like) – Source container holding all blocks.

• e_g – Selector for the first-stage error direction block.

• A – Selectors resolved and passed to relative_wellposedness_effective_diagnostic().

• C – Selectors resolved and passed to relative_wellposedness_effective_diagnostic().

• C_prime – Selectors resolved and passed to relative_wellposedness_effective_diagnostic().

• B – Optional selector accepted for interface consistency with (A, B, C, C') notation; ignored by this diagnostic.

• mask_s (array-like, str, or callable, optional) – Optional subset selectors for stage-specific sample restrictions.

• mask_t (array-like, str, or callable, optional) – Optional subset selectors for stage-specific sample restrictions.

• **kwargs – Forwarded to relative_wellposedness_effective_diagnostic().

Returns

Output dictionary returned by relative_wellposedness_effective_diagnostic().

Return type

dict

Notes

Resolved A, C, C_prime, and e_g must be row-aligned.