imputeR Package — mice.impute.imputeR.lmFun" />

The imputation methods "imputeR.lmFun" and "imputeR.cFun" provide interfaces to imputation methods in the imputeR package for continuous and binary data, respectively.

mice.impute.imputeR.lmFun(y, ry, x, Fun=NULL, draw_boot=TRUE, add_noise=TRUE, ... )

mice.impute.imputeR.cFun(y, ry, x, Fun=NULL, draw_boot=TRUE, ... )

Arguments

y

Incomplete data vector of length n

ry

Vector of missing data pattern (FALSE -- missing, TRUE -- observed)

x

Matrix (n x p) of complete covariates.

Fun

Name of imputation functions in imputeR package, e.g., imputeR::ridgeR, see Details.

draw_boot

Logical indicating whether a Bootstrap sample is taken for sampling model parameters

add_noise

Logical indicating whether empirical residuals should be added to predicted values

...

Further arguments to be passed

Details

Methods for continuous variables:

imputeR::CubistR, imputeR::glmboostR, imputeR::lassoR, imputeR::pcrR, imputeR::plsR, imputeR::ridgeR, imputeR::stepBackR, imputeR::stepBothR, imputeR::stepForR

Methods for binary variables: imputeR::gbmC, imputeR::lassoC, imputeR::ridgeC, imputeR::rpartC, imputeR::stepBackC, imputeR::stepBothC, imputeR::stepForC

Value

A vector of length nmis=sum(!ry) with imputed values.

Examples

if (FALSE) {
#############################################################################
# EXAMPLE 1: Example with binary and continuous variables
#############################################################################

library(mice)
library(imputeR)

data(nhanes, package="mice")
dat <- nhanes
dat$hyp <- as.factor(dat$hyp)

#* define imputation methods
method <- c(age="",bmi="norm",hyp="imputeR.cFun",chl="imputeR.lmFun")
Fun <- list( hyp=imputeR::ridgeC, chl=imputeR::ridgeR)

#** do imputation
imp <- mice::mice(dat1, method=method, maxit=10, m=4, Fun=Fun)
summary(imp)
}