Sample size required to achieve target confidence of freedom
This utility calculates the sample size required to achieve a desired level of confidence of population freedom. Can be applied at the cluster (herd/flock) level or population level. If applied at the cluster level, sensitivity and design prevalence are unit (animal) level values, whereas if applied at the population level, sensitivity and design prevalence are cluster level values.
- - the unit or cluster level sensitivity for the sampling;
- - prior confidence of freedom (from previous analyses or opinion);
- - probability of introduction of disease during the surveillance period;
- - the required level of confidence of freedom after the additional surveillance;
- - population size (optional); and
- - the design prevalence as either a proportion or an integer number of units/clusters.
Enter test sensitivity if the target is a cluster level freedom or cluster-sensitivity if the target is a system or population level freedom. If population size is entered the hypergeometric approximation is used, otherwise the calculation is based on the binomial distribution.
The main outputs are:
- - the adjusted prior confidence of freedom (taking into account the probability of introduction while the surveillance is being undertaken);
- - the target cluster or system sensitivity required to achieve the required confidence of freedom; and
- - the sample size required to achieve the target cluster or system sensitivity and resulting confidence of freedom.
A sample size of "n>N" indicates that it is not possible to achieve the desired level of confidence by testing the entire population. This most commonly occurs with low design prevalence and poor unit sensitivity of the test in a finite population.