Dear all
There was recently some discussion regarding how to calculate sample
sizes for studies that evaluate the diagnostic accuracy of a test. This
involved asking how precise an estimate of sensitivity and specificity
was required. How would one calculate the necessary sample size to
demonstrate the mean diagnostic accuracy between two groups of observers
in comparison with a "gold" standard as being statistically significant?
I would be extremely grateful for any suggestions or useful references.
Stephen Brealey
University of York
Department of Health Sciences
And Clincal Evaluation
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|