RSurveillance (version 0.2.1)

sep.rb.hypergeo.varse: Hypergeometric risk-based population sensitivity for varying unit sensitivity

Description

Calculates population sensitivity for a single risk factor and varying unit sensitivity using hypergeometric approximation method (assumes known population size)

Usage

sep.rb.hypergeo.varse(pstar, rr, N, df)

Arguments

pstar

design prevalence (scalar)

rr

relative risk values (vector of values corresponding to the number of risk strata)

N

vector of population size for each risk group, corresponding to rr values (vector of equal length to rr)

df

dataframe of values for each combination of risk stratum and sensitivity level, col 1 = risk group index, col 2 = unit Se, col 3 = n (sample size for risk group and unit sensitivity)

Value

list of 5 elements, a scalar of population-level sensitivity a vector of EPI values, a vector of corresponding Adjusted risks a vector of sample sizes (n) per risk group and a vector of mean unit sensitivities per risk group

Examples

# NOT RUN {
# examples for sep.rb.hypergeo.varse
rg<- c(1, 1, 2, 2)
se<- c(0.92, 0.85, 0.92, 0.85)
n<- c(80, 30, 20, 30)
df<- data.frame(rg, se, n)
sep.rb.hypergeo.varse(0.01, c(5, 1), c(200, 1800), df)

rg<- c(1, 1, 2, 2)
se<- c(0.95, 0.8, 0.95, 0.8)
n<- c(20, 10, 10, 5)
df<- data.frame(rg, se, n)
sep.rb.hypergeo.varse(0.05, c(3, 1), c(100, 400), df)

rg<- c(rep(1, 30), rep(2, 15))
se<- c(rep(0.95, 20), rep(0.8, 10), rep(0.95, 10), rep(0.8, 5))
n<- rep(1, 45)
df<- data.frame(rg, se, n)
sep.rb.hypergeo.varse(0.02, c(3, 1), c(100, 400), df)

rg<- c(1, 2, 3, 1, 2, 3)
se<- c(0.95, 0.95, 0.95, 0.8, 0.8, 0.8)
n<- c(20, 10, 10, 30, 5, 5)
df<- data.frame(rg, se, n)
sep.rb.hypergeo.varse(0.01, c(5, 3, 1), c(100, 300, 600), df)
# }