This utility calculates the expected probability of numbers of false positive results
to a test for a given sample size and test specificity, assuming the sample is from an uninfected population. It answers the question:
'For a given sample size and test specificity, and assuming that all animals are uninfected, what is the probability that there will be 1, 2, 3 etc false positives ?'.
It also answers the related questions: 'What is the probability of x (1, 2, 3, etc) or more false positive results? and
What is the probability of x (1, 2, 3, etc) or less false positive results?'
- Test unit specificity; and
- Sample size.
A table and plot of probabilities for each of the following:
- the likely numbers of false positives (x);
- less than or equal to x false positives; and
- greater than or equal to x false positives.
There is no simple formula for these caclulations, which utilise the properties of the binomial
probability distribution in R or excel. See example scripts/spreadsheet for details.
Vose, 2000, Risk analysis: A quantitative guide, 2nd ed. John wiley & Sons Ltd, Chichester, UK. pp 106-108.
Binomial probability distribution