Key result
The Bland-Altman limits of agreement method should be used instead of correlation coefficients to properly assess whether a new clinical measurement method can replace a standard one.
Answers are grounded in this paper and cite their sources.
Highlights the importance of using appropriate statistical methods, such as the Bland-Altman limits of agreement, rather than correlation, to assess new clinical measurement methods.
described frequently 4 but that approach is still in use.In brief, correlation assesses overall association across many measurements not individual agreement, and thus does not address a clinically relevant question.It is clear that peer review does not prevent the publication of papers with inappropriate statistical methods.And once faulty methods are in the literature, they will be copied.When assessing a new measurement method, we may wish to answer questions such as:
No takes yet. Share an insight, caveat, or question.
Douglas G. Altman (2009) conducted an editorial in Clinical measurement. Bland-Altman limits of agreement method vs. Correlation coefficient was evaluated. The Bland-Altman limits of agreement method should be used instead of correlation coefficients to properly assess whether a new clinical measurement method can replace a standard one.
Synapse has enriched 10 related papers. Consider them for comparative context: