rsu.sep.rb1rf {epiR}

Surveillance system sensitivity assuming risk-based sampling on one risk factor

Description

Calculates risk-based surveillance system (population-level) sensitivity with a single risk factor, assuming one-stage risk-based sampling and allowing unit sensitivity to vary among risk strata.

Usage

rsu.sep.rb1rf(N, n, rr, ppr, pstar, se.u, method = "binomial")

Arguments

N

scalar or vector of the same length as that vector of rr defining the population size per risk strata. Ignored if method = "binomial".

n

scalar or vector of the same length as that vector of rr defining the sample size per risk strata.

rr

scalar or vector of the same length as that vector of ppr defining the relative risk values.

ppr

scalar or vector of the same length as that vector of rr defining the population proportions in each risk strata. Ignored if method = "hypergeometric".

pstar

scalar, defining the design prevalence.

se.u

scalar or vector of the same length as that vector of rr defining the unit sensitivity (which can vary across strata).

method

character string indicating the method to be used. Options are binomial or hypergeometric. See details, below.

Details

If method = binomial N is ignored and values for ppr need to be entered. Conversely, if method = hypergeometric, ppr is ignored and calculated from N.

Value

A list comprised of two elements:

se.p

scalar, surveillance system (population-level) sensitivity estimates.

epi

vector, effective probability of infection estimates.

adj.risk

vector, adjusted relative risk estimates.

Examples

## EXAMPLE 1:
## A cross-sectional study is to be carried out to confirm the absence of 
## disease using one-stage risk based sampling. Assume a design prevalence of 
## 0.10 at the cluster (herd) level and the total number of clusters in 
## the population is unknown. Clusters are categorised as being either high, 
## medium or low risk with the probability of disease for clusters in the 
## high and medium risk area 5 and 3 times the probability of disease in the 
## low risk area. The proportions of clusters in the high, medium and low risk 
## area are 0.10, 0.10 and 0.80, respectively and you elect to sample five 
## clusters from each of the three areas using a test with diagnostic 
## sensitivity of 0.90. What is the surveillance system sensitivity? 

rsu.sep.rb1rf(N = NA, n = c(5,5,5), rr = c(5,3,1), ppr = c(0.10,0.10,0.80),
   pstar = 0.10, se.u = 0.90, method = "binomial")

## The surveillance system sensitivity is 0.94.


## EXAMPLE 2:
## Same scenario as above, but this time assume we know how many clusters are
## in the high, medium and low risk areas: 10, 10 and 80, respectively. What is
## the surveillance system sensitivity?

rsu.sep.rb1rf(N = c(10,10,80), n = c(5,5,5), rr = c(5,3,1), ppr = NA, 
   pstar = 0.10, se.u = 0.90, method = "hypergeometric")

## The surveillance system sensitivity is 0.96, almost identical to that 
## calculated above where the binomial distribution was used to account for 
## not knowing the size of the cluster population at risk.