sampling (version 2.1)

mstage: Multistage sampling

Description

Implements multistage sampling with equal/unequal probabilities.

Usage

mstage(data, stage=c("stratified","cluster",""), varnames, size, 
       method=c("srswor","srswr","poisson","systematic"), pik, description=FALSE)

Arguments

data

data frame or data matrix; its number of rows is N, the population size.

stage

list of sampling type at each stage; the possible values are: "stratified", "cluster" and "" (without stratification or clustering). For multistage element sampling, this argument is not necessary.

varnames

list of stratification or clustering variables.

size

list of sample sizes (in the order in which the samples appear in the multistage sampling).

method

method to select units; the following methods are implemented: simple random sampling without replacement (srswor), simple random sampling with replacement (srswr), Poisson sampling (poisson), systematic sampling (systematic); if the method is not spe

pik

list of selection probabilities or auxiliary information used to compute them; this argument is only used for unequal probability sampling (Poisson, systematic). If an auxiliary information is provided, the function uses the

description

a message is printed if its value is TRUE; the message gives the number of selected units and the number of the units in the population. By default, its value is FALSE.

Value

• The function
  produces a list, which contains the stages (if m is this list, the stage i is m$'i' etc) and the following information:
• ID_unit
  the identifier of selected units at each stage.
• Prob_ number _stage
  the inclusion probability at stage 'number'.
• Prob
  the final unit inclusion probability given in the last stage; it is the product of the unit inclusion probabilities at each stage.
• Replicates
  if the method is "srswr", the number of replicates is also given.

See Also

cluster, strata, getdata

Examples

############
## Example 1
############
# Two-stage cluster sampling
# Uses the 'swissmunicipalities' data for drawing a sample of units
data(swissmunicipalities)
# the variable 'REG' (region) has 7 categories;
# it is used as clustering variable in the first-stage sample
# the variable 'CT' (canton) has 26 categories; 
# it is used as clustering variable in the second-stage sample
# 4 clusters (regions) are selected in the first-stage 
# 1 canton is selected in the second-stage from each sampled cluster 
# the method is simple random sampling without replacement 
# (equal probability, without replacement)
m=mstage(swissmunicipalities,stage=list("cluster","cluster"), varnames=list("REG","CT"),
size=list(4,c(1,1,1,1)), method="srswor")
# the first stage is m$'1' and the second stage is m$'2'
# extracts the observed data
# the order of the columns is different from the order in the swsissmunicipalities database
getdata(swissmunicipalities, m)
############
## Example 2
############
# Two-stage element sampling
# Example from An and Watts (New SAS procedures for Analysis of Sample Survey Data)
# Generates artificial data (a 235X3 matrix with 3 columns: state, region, income).
# The variable "state" has 2 categories ('nc' and 'sc'). 
# The variable "region" has 3 categories (1, 2 and 3).
# The variable "income" is generated using the U(0,1) distribution. 
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)),
100*runif(235))
names(data)=c("state","region","income")
# the method is simple random sampling with replacement
# 25 units are drawn in the first-stage
# in the second-stage, 10 units are drawn from the already 25 selected units
m=mstage(data,size=list(25,10),method="srswr") 
# extracts the observed data
getdata(data,m)
############
## Example 3
############
# One-stage stratified cluster sampling
# The same data as in Example 2
# the variable 'state' is used as stratification variable 
# 20 states are drawn in the first stratum and 10 states in the second stratum
# the variable 'region' is used as clustering variable
# 1 cluster (region) is drawn in each stratum
m=mstage(data, stage=list("stratified","cluster"), varnames=list("state","region"), 
size=list(c(20,10),c(1,1)),method="srswor") 
# extracts the observed data
getdata(data,m)
############
## Example 4
############
# Two-stage cluster sampling
# The same data as in Example 1
data(swissmunicipalities)
# in the first-stage, the clustering variable is 'REG' (region) with 7 categories
# each region is selected with the probability 1/7
# in the second-stage, the clustering variable is 'CT'(canton) with 26 categories
# in the region 1, there are 3 cantons and each canton is selected with the probability 1/3
# in the region 2, there are 5 cantons and each canton is selected with the probability 1/5
# in the region 3, there are 3 cantons and each canton is selected with the probability 1/3
# in the region 4, there is 1 canton, which it is selected with the probability 1
# in the region 5, there are 7 cantons and each canton is selected with the probability 1/7
# in the region 6, there are 6 cantons and each canton is selected with the probability 1/6
# in the region 7, there is 1 canton, which it is selected with the probability 1
# it is necessary to use a list of selection probabilities at each stage
# prob is the list of the selection probabilities
# the method is systematic sampling (unequal probabilities, without replacement)
# 4 clusters (regions) are drawn in the first-stage 
# 1 cluster (canton) is drawn from each selected region in the second-stage
# ls is the list of sizes
ls=list(4,c(1,1,1,1))
prob=list(rep(4/7,7),list(rep(1/3,3),rep(1/5,5),rep(1/3,3),rep(1,1),rep(1/7,7),
rep(1/6,6),rep(1,1)))
m=mstage(swissmunicipalities,stage=list("cluster","cluster"),varnames=list("REG","CT"),
size=ls, method="systematic",pik=prob)
# extracts the observed data
getdata(swissmunicipalities,m)