Functions for Analysis of Nested Multiply Imputed Datasets
The function NestedImputationList takes a list of lists of datasets
and converts this into an object of class NestedImputationList.
Statistical models can be estimated with the function
with.NestedImputationList.
The mitools::MIcombine
method can be used for objects of class
NestedImputationResultList which are the output of
with.NestedImputationList.
NestedImputationList( datasets ) ## S3 method for class 'NestedImputationList' print(x, ...) ## S3 method for class 'NestedImputationResultList' MIcombine(results, ...)
datasets |
List of lists of datasets which are created by nested multiple imputation. |
x |
Object of class |
results |
Object of class |
... |
Further arguments to be passed. |
Function NestedImputationList: Object of class NestedImputationList.
Function MIcombine.NestedImputationList:
Object of class mipo.nmi.
## Not run:
#############################################################################
# EXAMPLE 1: Nested multiple imputation and conversion into an object of class
# NestedImputationList
#############################################################################
library(BIFIEsurvey)
data(data.timss2, package="BIFIEsurvey" )
datlist <- data.timss2
# remove first four variables
M <- length(datlist)
for (ll in 1:M){
datlist[[ll]] <- datlist[[ll]][, -c(1:4) ]
}
# nested multiple imputation using mice
imp1 <- miceadds::mice.nmi( datlist, m=3, maxit=2 )
summary(imp1)
# create object of class NestedImputationList
datlist1 <- miceadds::mids2datlist( imp1 )
datlist1 <- miceadds::NestedImputationList( datlist1 )
# estimate linear model using with
res1 <- with( datlist1, stats::lm( ASMMAT ~ female + migrant ) )
# pool results
mres1 <- mitools::MIcombine( res1 )
summary(mres1)
coef(mres1)
vcov(mres1)
## End(Not run)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.