Subsetting Multiply Imputed Datasets and Nested Multiply Imputed Datasets

Returns a subsets of multiply imputed datasets or nested multiply imputed datasets. These function allows choosing parts of the imputed datasets using the index argument for multiply imputed datasets and index_between and index_within for nested multiply imputed datasets as well as the application of the base::subset S3 method for selecting cases and variables in datasets.

subset_datlist(datlist, subset=TRUE, select=NULL, expr_subset=NULL,
        index=NULL, toclass="datlist")

# S3 method for datlist
subset(x, subset, select=NULL, expr_subset=NULL,
                     index=NULL, ...)
# S3 method for imputationList
subset(x, subset, select=NULL, expr_subset=NULL,
                     index=NULL, ...)
# S3 method for mids
subset(x, subset, select=NULL, expr_subset=NULL,
                     index=NULL, ...)
# S3 method for mids.1chain
subset(x, subset, select=NULL, expr_subset=NULL,
                     index=NULL, ...)

subset_nested.datlist( datlist, subset=TRUE, select=NULL, expr_subset=NULL,
      index_between=NULL, index_within=NULL, toclass="nested.datlist",
          simplify=FALSE )

# S3 method for nested.datlist
subset(x, subset, select=NULL, expr_subset=NULL,
                index_between=NULL, index_within=NULL, simplify=FALSE, ...)
# S3 method for NestedImputationList
subset(x, subset, select=NULL, expr_subset=NULL,
                index_between=NULL, index_within=NULL, simplify=FALSE, ...)

Arguments

datlist: For subset_datlist it is a list of datasets or an object of class datlist, imputationList, mids or mids.1chain.
For subset_nested.datlist it is a list of datasets or an object of class nested.datlist or NestedImputationList.
subset: Logical expression indicating elements or rows to keep, see base::subset. subset can also be a numeric vector containing row indices.
select: Expression indicating columns to select from a data frame
expr_subset: Expression indicating a selection criterion for selection rows.
index: Vector of indices indicating which of the multiply imputed datasets should be selected.
toclass: The object class in which the datasets should be saved.
index_between: Index for between nest datasets
index_within: Index for within nest datasets
simplify: Optional logical indicating whether a nested multiply imputed dataset should be simplified to a multiplied imputed dataset.
x: Object containing multiply imputed or nested multiply imputed datasets
...: Further arguments to be passed.

Value

For multiply imputed datasets: Object of class datlist, imputationList or mids

For nested multiply imputed datasets: Object of class nested.datlist or NestedImputationList.

Note

If subsetting is applied to objects of class mids (or mids.1chain), then informations about the imputation procedure are lost.

Examples

if (FALSE) {
#############################################################################
# EXAMPLE 1: Subsetting and selection of multiply imputed datasets
#############################################################################

data(data.ma02)

# define original list of datasets
datlist1a <- data.ma02
# object of class datlist
datlist1b <- miceadds::datlist_create(datlist1a)
datlist1b
# object of class imputationList
datlist1c <- mitools::imputationList(datlist1a)
datlist1c
# object of class mids
datlist1d <- miceadds::datlist2mids(datlist1a)
datlist1d

# select some imputed datasets
datlist2a <- miceadds::subset_datlist( datlist1a, index=c(5,3,7) )
datlist2a
# convert to class imputationList
datlist2b <- miceadds::subset_datlist( datlist1a, index=c(5,3,7),
                      toclass="imputationList")
datlist2b
# convert to class mids
datlist2c <- miceadds::subset_datlist( datlist1a, index=1:3, toclass="mids")
datlist2c

# select some variables
datlist3a <- miceadds::subset_datlist( datlist1a, select=c("idstud", "books")  )
datlist3a
# Because datlist1b is a datlist it is equivalent to
datlist3b <- subset( datlist1b, select=c("idstud", "books")  )
datlist3b
# operating on imputationList class
datlist3c <- miceadds::subset_datlist( datlist1c, select=c("idstud", "books")  )
datlist3c
# operating on mids class
datlist3d <- miceadds::subset_datlist( datlist1d, select=c("idstud", "books")  )
datlist3d
# selection of rows and columns in multiply imputed datasets
datlist4a <- miceadds::subset_datlist( datlist1a, index=1:5,
                  subset=datlist1a[[1]]$idschool < 1067,
                  select=c("idstud", "idschool","hisei") )
datlist4a
# convert to class mids
datlist4b <- miceadds::subset_datlist( datlist1a, index=1:5,
                  subset=datlist1a[[1]]$idschool < 1067,
                  select=c("idstud", "idschool","hisei"), toclass="mids" )
datlist4b
# The same functionality, but now applying to object of class mids datlist1d
datlist4c <- miceadds::subset_datlist( datlist1d, index=1:5,
               subset=datlist1a[[1]]$idschool < 1067,
               select=c("idstud", "idschool","hisei") )
datlist4c

# expression for selecting rows specific in each data frame
# which can result in differently sized datasets (because the variable
# migrant is imputed)
datlist5a <- miceadds::subset_datlist( datlist1a,  expr_subset=expression(migrant==1) )
datlist5a

# select the first 100 cases
datlist6a <- miceadds::subset_datlist( datlist1a, select=c("idstud", "books"),
                       subset=1:100 )
datlist6a

#############################################################################
# EXAMPLE 2: Subsetting and selection of nested multiply imputed datasets
#############################################################################

library(BIFIEsurvey)
data(data.timss4, package="BIFIEsurvey")
dat <- data.timss4

# create object of class 'nested.datlist'
datlist1a <- miceadds::nested.datlist_create( dat )
# create object of class 'NestedImputationList'
datlist1b <- miceadds::NestedImputationList(dat)

# select some between datasets
datlist2a <- subset_nested.datlist( datlist1a, index_between=c(1,3,4) )
datlist2a
# shorter version
datlist2b <- subset( datlist1a, index_between=c(1,3,4) )
datlist2b
# conversion of a NestedImputationList
datlist2c <- subset( datlist1b, index_between=c(1,3,4))
datlist2c
# select rows and columns
sel_cases <- datlist1a[[1]][[1]]$JKZONE <=42
datlist3a <- subset( datlist1a, subset=sel_cases,
                 select=c("IDSTUD","books", "ASMMAT") )
datlist3a
# remove within nest
datlist4a <- subset( datlist1a, index_within=1 )
datlist4a
# remove within nest and simplify structure
datlist4b <- subset( datlist1a, index_within=1, simplify=TRUE)
datlist4b
datlist4c <- subset( datlist1b, index_within=1, simplify=TRUE)
datlist4c
# remove between nest
datlist5a <- subset( datlist1a, index_between=1, simplify=TRUE)
datlist5a
datlist5b <- subset( datlist1b, index_between=1, simplify=TRUE)
datlist5b
}

Subsetting Multiply Imputed Datasets and Nested Multiply Imputed Datasets

Arguments

Value

Note

See also

Examples