getBiasRSampleBased:

In BERENZ/RISQ: What the package does (short line)

Usage

getBiasRSampleBased(prop, z, sigma, sampleDesign)

Arguments

prop
z
sigma
sampleDesign

Examples

##---- Should be DIRECTLY executable !! ----
##-- ==>  Define data, use random,
##--	or do  help(data=index)  for the standard data sets.

## The function is currently defined as
function (prop, z, sigma, sampleDesign) 
{
    nPopulation <- sum(sampleDesign$weights)
    propVar <- sampleDesign$getVarTotal(sampleDesign, prop)
    z <- z * sqrt(sampleDesign$weights)
    lambda1 <- sum(apply(z, 1, function(zi) return(t(zi) %*% 
        sigma %*% zi)))
    lambda2 <- propVar/nPopulation
    bias <- (lambda1 - lambda2)/nPopulation
    return(bias)
  }

BERENZ/RISQ documentation built on May 5, 2019, 10:25 a.m.