20.1 Simple Sampling

Simple (random) Sampling

library(dplyr)
iris_df <- iris
set.seed(1)
sample_n(iris_df, 10)
#>    Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
#> 1           5.8         2.7          4.1         1.0 versicolor
#> 2           6.4         2.8          5.6         2.1  virginica
#> 3           4.4         3.2          1.3         0.2     setosa
#> 4           4.3         3.0          1.1         0.1     setosa
#> 5           7.0         3.2          4.7         1.4 versicolor
#> 6           5.4         3.0          4.5         1.5 versicolor
#> 7           5.4         3.4          1.7         0.2     setosa
#> 8           7.6         3.0          6.6         2.1  virginica
#> 9           6.1         2.8          4.7         1.2 versicolor
#> 10          4.6         3.4          1.4         0.3     setosa

library(sampling)
# set unique id number for each row
iris_df$id = 1:nrow(iris_df)

# Simple random sampling with replacement
srswor(10, length(iris_df$id))
#>   [1] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 0 0 1
#>  [38] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0
#>  [75] 0 0 0 0 1 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 0 0 0 1 0
#> [112] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
#> [149] 0 0

# Simple random sampling without replacement (sequential method)
srswor1(10, length(iris_df$id))
#>   [1] 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
#>  [38] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
#>  [75] 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0
#> [112] 0 1 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 0 0
#> [149] 0 0

# Simple random sampling with replacement
srswr(10, length(iris_df$id))
#>   [1] 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 1 0 0 0 1 1 0 0 0 0
#>  [38] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
#>  [75] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0
#> [112] 0 0 1 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0
#> [149] 0 0

library(survey)
data("api")
srs_design <- svydesign(data = apistrat,
                        weights = ~pw, 
                        fpc = ~fpc, 
                        id = ~1)

library(sampler)
rsamp(albania,
      n = 260,
      over = 0.1, # desired oversampling proportion
      rep = F)

Identify missing points between sample and collected data

alsample <- rsamp(df = albania, 544)
alreceived <- rsamp(df = alsample, 390)
rmissing(sampdf = alsample,
         colldf = alreceived,
         col_name = qvKod)