Skip to content

Statistical Sample Quotas Model Using Clustering

This model estimates the sample size needed in each subadministrative unit without finding disease to have high probability that prevalence is at or below a threshold. The model explicitly accounts for biological clusterings in the population and assumes simple random sampling.

Geographical Scale

  • Sub-administrative area

Required Data

  • Population size or population density of hosts

User Inputs

  • Average cluster size of hosts
  • Correlation
  • Sensitivity of the diagnostic test

Outputs

  • The number of randomly selected animals that need to be tested in each subadministrative unit to have high probability (95%) that disease prevalence in the overall population is at or below 0.5%, 1%, 1.5%, 2%, 3%, 4%, or 5%.

graph of sample size vs probability of freedom from disease at a given prevaence

Example of model output showing sample size required to substantiate disease prevalence below 1%.

More information