Package 'samplingin'

Example of Allocation Data

Description

Example of Allocation Data for Sampling Purposes

Usage

alokasi_dt

Format

alokasi_dt

A data frame with 34 rows and 3 columns:

kdprov

province code

jml_kabkota

Population or number of regencies/cities

n_primary

Sample Allocation

...

---

Select Samples Given its Parameters

Description

Samples selection using systematic or PPS (Probability Proportional to Size) sampling method.

Usage

doSampling(
  pop,
  alloc,
  nsample,
  type,
  strata = NULL,
  ident = c("kdprov", "kdkab"),
  implicitby = NULL,
  method = "systematic",
  auxVar = NA,
  seed = 1,
  predetermined_rn = NULL,
  is_secondary = FALSE,
  verbose = TRUE
)

Arguments

pop	pop dataframe
alloc	allocation dataframe
nsample	variable on alloc df as allocation sample
type	type value for sample classification ('U' = Primary Samples, 'P' = Secondary Samples)
strata	strata variable, must available on both pop and alloc dataframe
ident	group by on allocation dataframe
implicitby	variable used as implicit stratification
method	method of sampling : "systematic" (the default), "srs" or "pps"
auxVar	auxiliary variable for pps sampling (method = "pps")
seed	seed
predetermined_rn	predetermined random number variable on allocation dataframe, the default value is NULL, random number will be generated randomly
is_secondary	if the value is TRUE, it will maintains existing primary samples and selects units that have not been selected as samples (FALSE as default)
verbose	verbose (TRUE as default)

Value

list of population data ("pop"), selected samples ("sampledf"), and details of sampling process ("details")

Examples

library(samplingin)
library(magrittr)
library(dplyr)

# Simple Random Sampling (SRS)
dtSampling_srs = doSampling(
   pop         = pop_dt
   , alloc     = alokasi_dt
   , nsample   = "n_primary"
   , type      = "U"
   , ident     = c("kdprov")
   , method    = "srs"
   , auxVar    = "Total"
   , seed      = 7892
)

# Population data with flag sample
pop_dt = dtSampling_srs$pop

# Selected Samples
dsampel = dtSampling_srs$sampledf

# Details of sampling process
rincian = dtSampling_srs$details

# PPS Sampling
dtSampling_pps = doSampling(
   pop         = pop_dt
   , alloc     = alokasi_dt
   , nsample   = "n_primary"
   , type      = "U"
   , ident     = c("kdprov")
   , method    = "pps"
   , auxVar    = "Total"
   , seed      = 1234
)

# Population data with flag sample
pop_dt = dtSampling_pps$pop

# Selected Samples
dsampel = dtSampling_pps$sampledf

# Details of sampling process
rincian = dtSampling_pps$details

# Systematic Sampling
dtSampling_sys = doSampling(
   pop         = pop_dt
   , alloc     = alokasi_dt
   , nsample   = "n_primary"
   , type      = "U"
   , ident     = c("kdprov")
   , method    = "systematic"
   , seed      = 4321
)

# Population data with flag sample
pop_dt = dtSampling_sys$pop

# Selected Samples
dsampel = dtSampling_sys$sampledf

# Details of sampling process
rincian = dtSampling_sys$details

# Systematic Sampling (Secondary Samples)

alokasi_dt_p = alokasi_dt %>%
   mutate(n_secondary = 2 * n_primary)

dtSampling_sys_p = doSampling(
   pop           = dtSampling_sys$pop
   , alloc       = alokasi_dt_p
   , nsample     = "n_secondary"
   , type        = "P"
   , ident       = c("kdprov")
   , method      = "systematic"
   , seed        = 6789
   , is_secondary = TRUE
)

# Population data with flag sample
pop_dt = dtSampling_sys_p$pop

# Selected Samples
dsampel = dtSampling_sys_p$sampledf

# Details of sampling process
rincian = dtSampling_sys_p$details

# Systematic Sampling with predetermined random number (predetermined_rn parameter)

alokasi_dt_rn = alokasi_dt %>% rowwise() %>% mutate(ar = runif(n(),0,1)) %>% ungroup

dtSampling_sys = doSampling(
   pop         = pop_dt
   , alloc     = alokasi_dt_rn
   , nsample   = "n_primary"
   , type      = "U"
   , ident     = c("kdprov")
   , method    = "systematic"
   , predetermined_rn = "ar"
   , seed      = 4321
)

# Population data with flag sample
pop_dt = dtSampling_sys$pop

# Selected Samples
dsampel = dtSampling_sys$sampledf

# Details of sampling process
rincian = dtSampling_sys$details

---

Allocate Predetermined Allocations to Smaller Levels

Description

Allocate predetermined allocations to smaller levels using proportional allocation method

Usage

get_allocation(data, n_alloc, group, pop_var = "jml", secondary = 0)

Arguments

data	population tabulation dataframe
n_alloc	total allocation dataframe
group	group of allocation level to be obtained
pop_var	population variable in data
secondary	how many times the secondary sample compares to primary sample

Value

allocation at more detailed level

Examples

library(samplingin)
library(magrittr)

contoh_alokasi = alokasi_dt %>%
   dplyr::select(-n_primary) %>%
   dplyr::mutate(nasional = 1)

alokasi_dt = get_allocation(
   data = contoh_alokasi
   , n_alloc = 100
   , group = c("nasional")
   , pop_var = "jml_kabkota"
)

---

Indonesian Population (SP2020)

Description

Tabulation of Indonesia's population based on the results of the 2020 population census by regency/city and gender

Usage

pop_dt

Format

pop_dt

A data frame with 514 rows and 8 columns:

idkab

region id

kdprov

province code

kdkab

regency/city code

nmprov

province name

nmkab

regency/city name

Laki-laki

Male Population

Perempuan

Female Population

Total

Total Population

...

Source

https://sensus.bps.go.id/main/index/sp2020

---

round_preserve_sum

Description

round_preserve_sum

Usage

round_preserve_sum(x, digits = 0)

Arguments

x	a number
digits	0 (default)

---