rsu.sssep.rs2st {epiR}

Sample size to achieve a desired surveillance system sensitivity assuming two-stage sampling

Description

Calculates the required sample size to achieve a desired surveillance system sensitivity assuming two-stage sampling (sampling of clusters and sampling of units within clusters), imperfect test sensitivity and perfect test specificity.

Usage

rsu.sssep.rs2st(H = NA, N = NA, pstar.c, se.c, pstar.u, se.u, se.p)

Arguments

H

scalar, integer representing the total number of clusters in the population. Use NA if unknown.

N

vector, integer representing the number of units within each cluster. Use NA if unknown.

pstar.c

scalar, numeric (0 to 1) representing the cluster level design prevalence.

se.c

scalar, numeric (0 to 1) representing the required cluster level sensitivity.

pstar.u

scalar, numeric (0 to 1) representing the surveillance unit level design prevalence.

se.u

scalar (0 to 1) representing the sensitivity of the diagnostic test at the surveillance unit level.

se.p

scalar (0 to 1) representing the desired surveillance system (population-level) sensitivity.

Value

A list comprised of two data frames: clusters and units. Data frame clusters lists:

H

the total number of clusters in the population, as entered by the user.

nsample

the number of clusters to be sampled.

Data frame units lists:

N

the number of units within each cluster, as entered by the user.

nsample

the number of units to be sampled.

References

Cameron A, Baldock C (1998). A new probability formula for surveys to substantiate freedom from disease. Preventive Veterinary Medicine 34: 1 - 17.

Cameron A (1999). Survey Toolbox for Livestock Diseases — A practical manual and software package for active surveillance of livestock diseases in developing countries. Australian Centre for International Agricultural Research, Canberra, Australia.

MacDiarmid S (1988). Future options for brucellosis surveillance in New Zealand beef herds. New Zealand Veterinary Journal 36: 39 - 42.

Martin S, Shoukri M, Thorburn M (1992). Evaluating the health status of herds based on tests applied to individuals. Preventive Veterinary Medicine 14: 33 - 43.

Examples

## EXAMPLE 1:
## Sampling is to be carried out to support a claim that a country is free
## of bovine brucellosis. We are not certain of the total number of herds
## in the country and we are not certain of the number of cows within each
## herd. 

## The design prevalence for this study is set to 0.01 at the herd level and
## if a herd is positive for brucellosis the individual animal level 
## design prevalence is set to 0.10. The sensitivity of the diagnostic 
## test to be used is 0.95. 

## How many herds and how many animals from within each herd 
## need to be sampled to be 95% confident of detecting disease at the 
## herd and individual animal level? 

rsu.sssep.rs2st(H = NA, N = NA, pstar.c = 0.01, se.c = 0.95, 
   pstar.u = 0.10, se.u = 0.95, se.p = 0.95)
   
## A total of 314 herds need to be sampled, 31 cows from each herd.


## EXAMPLE 2:
## Now lets say we know that there are 500 cattle herds in the country and
## we have the results of a recent livestock census providing counts of the 
## number of cattle in each herd. How many herds and how many animals from
## within each herd need to be sampled to be 95% confident of detecting
## disease at the herd and individual animal level?

# Generate a vector of herd sizes. The minimum herd size is 25.

set.seed(1234)
hsize <- ceiling(rlnorm(n = 500, meanlog = 1.5, sdlog = 2)) + 25 

nsample <- rsu.sssep.rs2st(H = 500, N = hsize, pstar.c = 0.01, se.c = 0.95,  
   pstar.u = 0.10, se.u = 0.95, se.p = 0.95)
  
nsample$clusters
head(nsample$units)
 
## A total of 238 of the 500 herds need to be tested. The number of animals 
## to sample from the first herd (comprised of 26 animals) is 18.