Missing Data Imputation and Model Checking
Iterative Multiple Imputation from Conditional Distributions
Class "missing_variable" and Inherited Classes
Class "missing_data.frame"
Make Changes to Discretionary Characteristics of Missing Variables
Multiple Imputation
Convergence Diagnostics
Estimate a Model Pooling Over the Imputed Datasets
Extract the Completed Data
Class "allcategorical_missing_data.frame"
Class "bounded-continuous"
Class "categorical" and Inherited Classes
The "censored-continuous" Class, the "truncated-continuous" Class and ...
Class "continuous"
Class "count"
Class "experiment_missing_data.frame"
Wrappers To Fit a Model
An Extractor Function for Model Parameters
Histograms of Multiply Imputed Data
Class "irrelevant" and Inherited Classes
Internal Functions and Methods
Exports completed data in Stata (.dta) or comma-separated (.csv) forma...
Apply a Function to a Object of Class mi
Class "multilevel_missing_data.frame"
The multinomial family
Class "positive-continuous" and Inherited Classes
Generate a random data.frame with tunable characteristics
Class "semi-continuous" and Inherited Classes
The mi package provides functions for data manipulation, imputing missing values in an approximate Bayesian framework, diagnostics of the models used to generate the imputations, confidence-building mechanisms to validate some of the assumptions of the imputation algorithm, and functions to analyze multiply imputed data sets with the appropriate degree of sampling uncertainty.