model_impute: Model an imputed dataset

In ThierryO/multimput: Using Multiple Imputation to Address Missing Data

Description

Model an imputed dataset

Usage

model_impute(object, model.fun, rhs, model.args, extractor, extractor.args)

## S4 method for signature 'ANY'
model_impute(object, model.fun, rhs, model.args, extractor,
  extractor.args)

## S4 method for signature 'aggregatedImputed'
model_impute(object, model.fun, rhs, model.args,
  extractor, extractor.args)

Arguments

object	the imputed dataset
model.fun	the function to apply on each imputation set
rhs	the right hand side of the model
model.args	an optional list of arguments to pass to the model function.
extractor	a function which return a matrix or data.frame. The first column should contain the estimate, the second the standard error of the estimate
extractor.args	an optional list of arguments to pass to the extractor function.

Examples

dataset <- generateData(n.year = 10, n.site = 50, n.run = 1)
dataset$Count[sample(nrow(dataset), 50)] <- NA
model <- lm(Count ~ Year + factor(Period) + factor(Site), data = dataset)
imputed <- impute(data = dataset, model = model)
aggr <- aggregate_impute(imputed, grouping = c("Year", "Period"), fun = sum)
extractor <- function(model){
  summary(model)$coefficients[, c("Estimate", "Std. Error")]
}
model_impute(
  object = aggr,
  model.fun = lm,
  rhs = "0 + factor(Year)",
  extractor = extractor
)

ThierryO/multimput documentation built on May 9, 2019, 4:42 p.m.