Answers are grounded in this paper and cite their sources.
Merrill and Schweppe [1] propose a modification of the usual least squares criterion for estimation in order to suppress bad data. It is shown that similar estimators can be obtained from maximum likelihood theory.
No takes yet. Share an insight, caveat, or question.
J. Kohlas (1972) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: