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
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
|
\name{samplecube}
\alias{samplecube}
\title{Sample cube method}
\description{
Selects a balanced sample (a vector of 0 and 1) or an almost balanced sample.
Firstly, the flight phase is applied. Next, if needed, the landing phase is applied
on the result of the flight phase.
}
\usage{samplecube(X,pik,order=1,comment=TRUE,method=1)}
\arguments{
\item{X}{matrix of auxiliary variables on which the sample must be balanced.}
\item{pik}{vector of inclusion probabilities.}
\item{order}{ 1, the data are randomly arranged,\cr
2, no change in data order,\cr
3, the data are sorted in decreasing order.
}
\item{comment}{a comment is written during the execution if \code{comment} is \code{TRUE}.}
\item{method}{ 1, for a landing phase by linear programming,\cr
2, for a landing phase by suppression of variables.}
}
\seealso{
\code{\link{landingcube}}, \code{\link{fastflightcube}}
}
\references{
Till, Y. (2006), \emph{Sampling Algorithms}, Springer.\cr
Chauvet, G. and Till, Y. (2006). A fast algorithm of balanced sampling. \emph{Computational Statistics}, 21/1:53--62. \cr
Chauvet, G. and Till, Y. (2005). New SAS macros for balanced sampling. In INSEE, editor, \emph{Journes de Mthodologie Statistique}, Paris.\cr
Deville, J.-C. and Till, Y. (2004). Efficient balanced sampling: the cube method. \emph{Biometrika}, 91:893--912.\cr
Deville, J.-C. and Till, Y. (2005). Variance approximation under balanced sampling. \emph{Journal of Statistical Planning and Inference}, 128/2:411--425.
}
\examples{
############
## Example 1
############
# matrix of balancing variables
X=cbind(c(1,1,1,1,1,1,1,1,1),c(1.1,2.2,3.1,4.2,5.1,6.3,7.1,8.1,9.1))
# vector of inclusion probabilities
# the sample size is 3.
pik=c(1/3,1/3,1/3,1/3,1/3,1/3,1/3,1/3,1/3)
# selection of the sample
s=samplecube(X,pik,order=1,comment=TRUE)
# The selected sample
(1:length(pik))[s==1]
############
## Example 2
############
# 2 strata and 2 auxiliary variables
# we verify the values of the inclusion probabilities by simulations
X=rbind(c(1,0,1,2),c(1,0,2,5),c(1,0,3,7),c(1,0,4,9),
c(1,0,5,1),c(1,0,6,5),c(1,0,7,7),c(1,0,8,6),c(1,0,9,9),
c(1,0,10,3),c(0,1,11,3),c(0,1,12,2),c(0,1,13,3),
c(0,1,14,6),c(0,1,15,8),c(0,1,16,9),c(0,1,17,1),
c(0,1,18,2),c(0,1,19,3),c(0,1,20,4))
pik=rep(1/2,times=20)
ppp=rep(0,times=20)
sim=10 #for accurate results increase this value
for(i in (1:sim))
ppp=ppp+samplecube(X,pik,1,FALSE)
ppp=ppp/sim
print(ppp)
print(pik)
############
## Example 3
############
# unequal probability sampling by cube method
# one auxiliary variable equal to the inclusion probability
N=100
pik=runif(N)
pikfin=samplecube(array(pik,c(N,1)),pik,1,TRUE)
############
## Example 4
############
# p auxiliary variables generated randomly
N=100
p=7
x=rnorm(N*p,10,3)
# random inclusion probabilities
pik= runif(N)
X=array(x,c(N,p))
X=cbind(cbind(X,rep(1,times=N)),pik)
pikfin=samplecube(X,pik,1,TRUE)
############
## Example 5
############
# strata and an auxiliary variable
N=100
a=rep(1,times=N)
b=rep(0,times=N)
V1=c(a,b,b)
V2=c(b,a,b)
V3=c(b,b,a)
X=cbind(V1,V2,V3)
pik=rep(2/10,times=3*N)
pikfin=samplecube(X,pik,1,TRUE)
############
## Example 6
############
# Selection of a balanced sample using the MU284 population,
# Monte Carlo simulation and variance comparison with
# unequal probability sampling of fixed sample size.
############
data(MU284)
# inclusion probabilities, sample size 50
pik=inclusionprobabilities(MU284$P75,50)
# matrix of balancing variables
X=cbind(MU284$P75,MU284$CS82,MU284$SS82,MU284$S82,MU284$ME84,MU284$REV84)
# Horvitz-Thompson estimator for a balanced sample
s=samplecube(X,pik,1,FALSE)
HTestimator(MU284$RMT85[s==1],pik[s==1])
# Horvitz-Thompson estimator for an unequal probability sample
s=samplecube(matrix(pik),pik,1,FALSE)
HTestimator(MU284$RMT85[s==1],pik[s==1])
# Monte Carlo simulation; for a better accuracy, increase the value 'sim'
sim=5
res1=rep(0,times=sim)
res2=rep(0,times=sim)
for(i in 1:sim)
{
cat("Simulation number ",i,"\n")
s=samplecube(X,pik,1,FALSE)
res1[i]=HTestimator(MU284$RMT85[s==1],pik[s==1])
s=samplecube(matrix(pik),pik,1,FALSE)
res2[i]=HTestimator(MU284$RMT85[s==1],pik[s==1])
}
# summary and boxplots
summary(res1)
summary(res2)
ss=cbind(res1,res2)
colnames(ss) = c("balanced sampling","uneq prob sampling")
boxplot(data.frame(ss), las=1)
}
\keyword{survey}
\encoding{latin1}
|
