declare_sampling {DeclareDesign}

Declare sampling procedure

Description

Declare sampling procedure

Usage

declare_sampling(..., handler = sampling_handler, label = NULL)

sampling_handler(data, ..., legacy = FALSE)

Arguments

...

arguments to be captured, and later passed to the handler

handler

a tidy-in, tidy-out function

label

a string describing the step

data

A data.frame.

legacy

Use the legacy randomizr functionality. This will be disabled in future; please use legacy = FALSE.

Value

A sampling declaration, which is a function that takes a data.frame as an argument and returns a data.frame subsetted to sampled observations and (optionally) augmented with inclusion probabilities and other quantities.

Examples

 
# declare_sampling in use
## Two-arm randomized experiment
design <-
  declare_model(
    N = 500,
    X = rep(c(0, 1), each = N / 2),
    U = rnorm(N, sd = 0.25),
    potential_outcomes(Y ~ 0.2 * Z + X + U)
  ) +
  declare_inquiry(ATE = mean(Y_Z_1 - Y_Z_0)) +
  declare_sampling(S = complete_rs(N = N, n = 200)) +
  declare_assignment(Z = complete_ra(N = N, m = 100)) +
  declare_measurement(Y = reveal_outcomes(Y ~ Z)) +
  declare_estimator(Y ~ Z, inquiry = "ATE")
  
run_design(design)

# Set up population to sample from
model <- declare_model(
  villages = add_level(
    N = 30, 
    N_households = sample(c(50:100), N, replace = TRUE)
  ),
  households = add_level(
    N = N_households, 
    N_members = sample(c(1, 2, 3, 4), N, 
                       prob = c(0.2, 0.3, 0.25, 0.25), replace = TRUE)
  ),
  individuals = add_level(
    N = N_members, 
    age = sample(18:90, N, replace = TRUE),
    gender = rbinom(n = N, size = 1, prob = .5)
  )
)

# Sampling procedures
## Complete random sampling
design <- model +
  declare_sampling(S = complete_rs(N = N, n = 1000))
  
head(draw_data(design))

## Cluster random sampling
design <- model +
  declare_sampling(S = cluster_rs(clusters = villages, 
                                  n = 15))

head(draw_data(design))

## Strata and cluster random sampling
design <- model +
  declare_sampling(S  = strata_and_cluster_rs(
    strata = villages,
    clusters = households,
    strata_n = rep(20, 30)))
    
head(draw_data(design))

## Stratified random sampling
design <- model +
  declare_sampling(S = strata_rs(strata = gender, n = 100))

head(draw_data(design))