sampling (version 2.10)

rhg_strata: Response homogeneity groups for a stratified sampling

Description

Computes response homogeneity groups and the corresponding response probability for each unit into a group, for a stratified sampling.

Usage

rhg_strata(X,selection)

Value

The initial sample data frame and also the following components:

rhgroup

response homogeneity group for each unit, conditionally on its stratum.

prob_response

response probability for each unit; for the units with status=0, this probability is 0.

Arguments

X

sample data frame; it should contain the columns 'ID_unit','Stratum', and 'status'; 'ID_unit' denotes the unit identifier (a number); 'Stratum' denotes the unit stratum; 'status' is a 1/0 variable denoting the response/non-response of a unit in the sample.

selection

vector of variable names in X used to construct the groups.

Details

Into a response homogeneity group, the reponse probability is the same for all units. Data are missing at random within groups, conditionally on the selected sample.

References

Särndal, C.-E., Swensson, B. and Wretman, J. (1992). Model Assisted Survey Sampling. Springer

See Also

rhg, calib

Examples

############
## Example 1
############
# uses Example 2 from the 'strata' function help file
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")
# draws a sample
s1=strata(data,c("region","state"),size=c(10,5,10,4,6), method="systematic",
pik=data$income)
# extracts the observed data
s1=getdata(data,s1)
# randomly generates the 'status' variable (1-sample respondent, 0-otherwise)
status=ifelse(runif(nrow(s1))<0.3,0,1)
# adds the 'status' variable to the sample data frame s1
s1=cbind.data.frame(s1,status)
# creates classes of income using the median of income
# suppose that the income is available for all units in the sample
classincome=ifelse(s1$income