with_robosynth-list: Handle and analyze synthetic data

In simongrund1/robosynth: Robust Synthetic Data Generation with Data-Augmented Multiple Imputation

Handle and analyze synthetic data

Description

Functions for handling and analyzing a list of synthetic data sets.

Usage

## S3 method for class 'robosynth.list'
with(data, expr, ...)
## S3 method for class 'robosynth.list'
within(data, expr, ...)

Arguments

data	list of synthetic data sets as returned by extract.
expr	expression to be evaluated in each of the synthetic data sets.
...	not used.

Details

These functions can be used for data handling and for fitting statistical models in a list of synthetic data sets. The with function can be used to fit statistical models, where expr is a call to a model fitting function (e.g., lm or similar; see Examples). The within function can be used for various data handling tasks, for example, for transformations or to compute new variables (see Examples).

Formally, with evaluates expr in each data set and returns a list of results, whereas within evaluates expr in each data set and returns a list with the altered data sets.

Value

For with an object of class robosynth.result (a list of the results of the evaluated expression). For within an object of class robosynth.list (a list of synthetic data sets).

Author(s)

Simon Grund

See Also

extract

Examples

# create masked copies
sociosexuality <- within(sociosexuality, {
  m_sex <- mask.categorical(sex, probability = .80)
  m_sexpref <- mask.categorical(sexpref, probability = .60)
  m_age <- mask.continuous(age, reliability = .90)
})

# combine synthesis and masking models
models <- combine.models(

  synthesis.model(sex ~ 1, type = "binary"),
  synthesis.model(sexpref ~ 1 + sex, type = "categorical"),
  synthesis.model(age ~ 1 + sex + sexpref, type = "continuous"),

  masking.model(m_sex ~ sex, type = "binary"),
  masking.model(m_sexpref ~ sexpref, type = "categorical"),
  masking.model(m_age ~ age, type = "continuous"),

  data = sociosexuality

)

# run synthesis
syn <- synthesize(models = models, m = 5, iter = 5)

# extract synthetic data
synlist <- extract(syn)

# * Example 1: centering (within)

# centering
synlist <- within(synlist, {
  c_age <- age - mean(age)
})

# * Example 2: analysis (with)

# fit linear model
fit <- with(synlist, lm(behavior ~ age))

simongrund1/robosynth documentation built on March 20, 2022, 6:15 p.m.