Answers are grounded in this paper and cite their sources.
In this paper the identifiability problem is formulated as a dual of the data reduction problem in statistical inference. Some classical results in the theory of sufficient statistics are dualized in order to obtain criteria for finding “maximal identifiable statistics” in parametric models. Applications to identifiability of linear dynamical systems are discussed.
No takes yet. Share an insight, caveat, or question.
Giorgio Picci (1977) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: