n.hp: Hypergeometric (HerdPlus) sample size for finite population...

In RSurveillance: Design and Analysis of Disease Surveillance Activities

Description

Calculates sample size to achieve specified population sensitivity with population specificity >= specified minimum value, for given population size, cut-point number of positives and other parameters, all paramaters must be scalars

Usage

n.hp(N, sep = 0.95, c = 1, se, sp = 1, pstar, minSpH = 0.95)

Arguments

N	population size
sep	target population sensitivity
c	The cut-point number of positives to classify a cluster as positive, default=1, if positives < c result is negative, >= c is positive
se	test unit sensitivity
sp	test unit specificity, default=1
pstar	design prevalence as a proportion or integer (number of infected units)
minSpH	minimium desired population specificity

Value

A list of 2 elements, a dataframe with 1 row and six columns for the recommended sample size and corresponding values for population sensitivity (SeP), population specificity (SpP), N, c and pstar and a dataframe of n rows with SeP and SpP values for each value of n up to the recommended value. Returns sample size for maximum achievable sep if it is not possible to achieve target sep AND SpP>= minSpH.

Examples

# examples for n.hp
n.hp(65,0.95,c=1,se=0.95,sp=0.99,pstar=0.05, minSpH=0.9)[[1]]
n.hp(65,0.95,c=2,se=0.95,sp=0.99,pstar=0.05, minSpH=0.9)

RSurveillance documentation built on July 2, 2020, 2:33 a.m.