Hello,
I would like to do a study comparing a new diagnosis technique to a gold
standard for diagnosing heart failure. If I know the sensitivity and the
specificity of the new diagnosis technique, then which should I use in order
to calculate a sample size?
I was thinking of using the sensitivity, based on this I can estimate the
required sample size of those with the disease, then using the binomial
distribution estimate the total sample size required.
ANy feedback would be appreciated.
Esoult
_________________________________________________________________
Discover the magic of RSS feeds at MSN Ireland! http://ie.msn.com/
|