'Second order probabilities in stratified sample with probability proportional to size
I have a dataset that looks like this data looks something like this.
set.seed(135)
library(data.table)
# create dataset
dt <- data.table(units=c("Yves", "Ken", "Erik", "Sharon", "Leslie","Mark", "Emily"),
size= c(52, 60, 75, 100, 50,30,80),
strata= c("A", "A", "A","A", "B", "B", "B"))
print(dt)
units size strata
1: Yves 52 A
2: Ken 60 A
3: Erik 75 A
4: Sharon 100 A
5: Leslie 50 B
6: Mark 30 B
7: Emily 80 B
I have drawn a stratified sample with probability proportional to size using the TeachingSampling package
library(TeachingSampling)
# I determine the sample size in each stratum
mh <- c(2,2)
# Draw a stratified PPS sample with replacement of size n=4
res <- S.STpiPS(dt$strata, dt$size, mh)
# The selected sample
sam <- res[,1]
U[sam]
"Erik" "Sharon" "Leslie" "Emily"
Now let us assume that "Erik" refuses to take part in the survey and I need to sample a replacement. How can I make a the second call selection using second-order probabilities?.
thanks a lot for your help
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|
