Learn R Programming

NPBayesImpute (version 0.6)

Non-Parametric Bayesian Multiple Imputation for Categorical Data

Description

These routines create multiple imputations of missing at random categorical data, with or without structural zeros. Imputations are based on Dirichlet process mixtures of multinomial distributions, which is a non-parametric Bayesian modeling approach that allows for flexible joint modeling.

Copy Link

Version

Install

install.packages('NPBayesImpute')

Monthly Downloads

85

Version

0.6

License

GPL (>= 3)

Maintainer

Quanli Wang

Last Published

February 9th, 2016

Functions in NPBayesImpute (0.6)

MCZ

Example dataframe for structrual zeros.
X

Example dataframe for input categorical data with missing values.
CreateModel

Create and initialize the Rcpp_Lcm model object
Rcpp_Lcm

RCPP implemenation of the library
GetMCZ

Convert disjointed structrual zeros to a dataframe, using the same setting from original structrual zero data.
Rcpp_Lcm-class

Class "Rcpp_Lcm"
UpdateX

Allow user to update the model with data matrix of same kind.
Lcm

RCPP implemenation of the library
NPBayesImpute-package

Bayesian Multiple Imputation for Large-Scale Categorical Data with Structural Zeros
GetDataFrame

Convert imputed data to a dataframe, using the same setting from original input data.