1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
|
\name{postest}
\alias{postest}
\title{Poststratified estimator}
\description{Computes the poststratified estimator of the population total.}
\usage{postest(data, y, pik, NG, description=FALSE)}
\arguments{
\item{data}{data frame or data matrix; its number of rows is n, the sample size.}
\item{y}{vector of the variable of interest; its length is equal to n, the sample size.}
\item{pik}{vector of the first-order inclusion probabilities for the sampled units; its length is equal to n, the sample size.}
\item{NG}{vector of population frequency in each group G; for stratified sampling with poststratification,
NG is a matrix of population frequency in each cell GH.}
\item{description}{if TRUE, the estimator is printed for each poststratum; by default, FALSE.}
}
\seealso{
\code{\link{poststrata}}}
\examples{
############
## Example 1
############
#stratified sampling and poststratification
data(swissmunicipalities)
# the variable 'REG' has 7 categories in the population
# it is used as stratification variable
# Computes the population stratum sizes
table(swissmunicipalities$REG)
# do not run
# 1 2 3 4 5 6 7
# 589 913 321 171 471 186 245
# the sample stratum sizes are given by size=c(30,20,45,15,20,11,44)
# the method is simple random sampling without replacement
st=strata(swissmunicipalities,stratanames=c("REG"),
size=c(30,20,45,15,20,11,44), method="srswor")
# extracts the observed data
# the order of the columns is different from the order in the initial data
x=getdata(swissmunicipalities, st)
px=poststrata(x,"REG")
#computes the population frequency in each group
ct=unique(px$data$REG)
yy=table(swissmunicipalities$REG)[ct]
postest(px$data,y=px$data$Pop020,pik=px$data$Prob,NG=diag(yy))
HTstrata(x$Pop020,x$Prob,x$Stratum)
#the two estimators are equal
############
## Example 2
############
# systematic sampling and poststratification
data(belgianmunicipalities)
Tot=belgianmunicipalities$Tot04
name=belgianmunicipalities$Commune
pik=inclusionprobabilities(Tot,200)
#selects a sample
s=UPsystematic(pik)
#the sample is
which(s==1)
# extracts the observed data
b=getdata(belgianmunicipalities,s)
pb=poststrata(b,"Province")
#computes the population frequency in each group
ct=unique(pb$data$Province)
yy=table(belgianmunicipalities$Province)[ct]
postest(pb$data,y=pb$data$TaxableIncome,pik=pik[s==1],NG=yy,description=TRUE)
HTestimator(pb$data$TaxableIncome,pik=pik[s==1])
############
## Example 3
############
#cluster sampling and postratification
data(swissmunicipalities)
# the variable 'REG' has 7 categories in the population
# it is used as clustering variable
# the sample size is 3; the method is simple random sampling without replacement
cl=cluster(swissmunicipalities,clustername=c("REG"),size=3,method="srswor")
# extracts the observed data
# the order of the columns is different from the order in the initial data
c=getdata(swissmunicipalities, cl)
pc=poststrata(c,"CT")
#computes the population frequency in each group
ct=unique(pc$data$CT)
yy=table(swissmunicipalities$CT)[ct]
postest(pc$data,y=pc$data$Pop020,pik=pc$data$Prob,NG=yy,description=TRUE)
############
## Example 4
############
#postratification with two criteria
#artificial data
data=rbind(matrix(rep("nc",165),165,1,byrow=TRUE),matrix(rep("sc",70),70,1,byrow=TRUE))
data=cbind.data.frame(data,c(rep(1,100), rep(2,50), rep(3,15), rep(1,30),rep(2,40)),
1000*runif(235))
names(data)=c("state","region","income")
# computes the population stratum sizes
table(data$region,data$state)
# not run
# nc sc
# 1 100 30
# 2 50 40
# 3 15 0
#selects a sample of size 10
s=srswor(10,nrow(data))
# postratification using region and state
ps=poststrata(data[s==1,],c("region","state"))
#computes the population frequency in each group
ct=unique(ps$data$poststratum)
yy=numeric(length(ct))
for(i in 1:length(ct))
{
xy=ps$data[ps$data$poststratum==ct[i],]
xstate=unique(xy$state)
ystate=unique(xy$region)
xx=data[data$state==xstate & data$region==ystate,]
yy[i]=nrow(xx)
}
postest(ps$data,y=ps$data$income,pik=rep(10/nrow(data),10),NG=yy,description=TRUE)
}
\keyword{survey}
|
