BISSERY Alvine <[email protected]> wrote:
> I want to estimate the specifity of a test. Response of the
> test are : "disease", "not disease", and "i don't know" The
> gold standart gives : "disease" , "not disease". What do I
> have to do with the answer "I don't know" .. how can I estimate
> the specificity ?
You can compute the estimate the usual way: the specificity is
the conditional probability that the test will be negative given
a negative result of the gold standard.
Therefore, the specificity equals the number of samples with a
negative test result divided by the total number of tested
samples with a negative gold standard result. Inconclusive
results will be classified as non-negative for the computation of
the specificity.
Likewise, inconclusive results will be classified as non-positive
for the computation of the sensitivity. In other words,
inconclusive results may greatly decrease the diagnostic value of
a test.
--
Philippe Glaziou
Pasteur Institute of Cambodia
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
