06pool {mi}

Estimate a Model Pooling Over the Imputed Datasets

Description

This function estimates a chosen model, taking into account the additional uncertainty that arises due to a finite number of imputations of the missing data.

Usage

pool(formula, data, m = NULL, FUN = NULL, ...)

Arguments

formula

a formula in the same syntax as used by glm

data

an object of mi-class

m

number of completed datasets to average over, which if NULL defaults to the number of chains used in mi

FUN

Function to estimate models or NULL which uses the same function as used in the fit_model-methods for the dependent variable

...

further arguments passed to FUN

Details

FUN is estimated on each of the m completed datasets according to the given formula and the results are combined using the Rubin Rules.

Value

An object of class "pooled" whose definition is subject to change but it has a summary and display method.

Author(s)

Ben Goodrich and Jonathan Kropko, for this version, based on earlier versions written by Yu-Sung Su, Masanao Yajima, Maria Grazia Pittau, Jennifer Hill, and Andrew Gelman.

See Also

mi

Examples

if(!exists("imputations", env = .GlobalEnv)) {
  imputations <- mi:::imputations # cached from example("mi-package")
}
analysis <- pool(ppvtr.36 ~ first + b.marr + income + momage + momed + momrace, 
                 data = imputations)
display(analysis)