Groupwise computations within data frames

Here we use data from the British Election Study 2010. The data set bes2010feelings-pre-long.RData is prepared from the original available at https://www.britishelectionstudy.com/data-object/2010-bes-cross-section/ by removing identifying information and scrambling the data.

load("bes2010feelings-pre-long.RData")

Groupwise computations using split():

bes2010flngs_pre_long.splt <- split(bes2010flngs_pre_long,
                                    bes2010flngs_pre_long$id)

str(bes2010flngs_pre_long.splt[[1]])

'data.frame':	8 obs. of  5 variables:
 $ region      : Factor w/ 3 levels "England","Scotland",..: 1 1 1 1 1 1 1 1
 $ party       : Factor w/ 8 levels "Conservative",..: 1 2 3 4 5 6 7 8
 $ flng.leaders: num  3 6 3 NA 5 NA NA NA
 $ flng.parties: num  6 5 4 NA NA 7 3 0
 $ id          : int  1 1 1 1 1 1 1 1
 - attr(*, "reshapeLong")=List of 4
  ..$ varying:List of 2
  .. ..$ flng.leaders: chr [1:8] "flng.cameron" "flng.brown" "flng.clegg" "flng.salmond" ...
  .. ..$ flng.parties: chr [1:8] "flng.cons" "flng.labour" "flng.libdem" "flng.snp" ...
  ..$ v.names: chr [1:2] "flng.leaders" "flng.parties"
  ..$ idvar  : chr "id"
  ..$ timevar: chr "party"

Mean <- function(x,...) mean(x,...,na.rm=TRUE)

bes2010flngs_pre_long.splt <- lapply(
    bes2010flngs_pre_long.splt,
    within,expr={
        rel.flng.parties <- flng.parties - Mean(flng.parties)
        rel.flng.leaders <- flng.leaders - Mean(flng.leaders)
    })

str(bes2010flngs_pre_long.splt[[1]])

'data.frame':	8 obs. of  7 variables:
 $ region          : Factor w/ 3 levels "England","Scotland",..: 1 1 1 1 1 1 1 1
 $ party           : Factor w/ 8 levels "Conservative",..: 1 2 3 4 5 6 7 8
 $ flng.leaders    : num  3 6 3 NA 5 NA NA NA
 $ flng.parties    : num  6 5 4 NA NA 7 3 0
 $ id              : int  1 1 1 1 1 1 1 1
 $ rel.flng.leaders: num  -1.25 1.75 -1.25 NA 0.75 NA NA NA
 $ rel.flng.parties: num  1.833 0.833 -0.167 NA NA ...
 - attr(*, "reshapeLong")=List of 4
  ..$ varying:List of 2
  .. ..$ flng.leaders: chr [1:8] "flng.cameron" "flng.brown" "flng.clegg" "flng.salmond" ...
  .. ..$ flng.parties: chr [1:8] "flng.cons" "flng.labour" "flng.libdem" "flng.snp" ...
  ..$ v.names: chr [1:2] "flng.leaders" "flng.parties"
  ..$ idvar  : chr "id"
  ..$ timevar: chr "party"

bes2010flngs_pre_long <- unsplit(bes2010flngs_pre_long.splt,
                                 bes2010flngs_pre_long$id)
str(bes2010flngs_pre_long)

'data.frame':	15480 obs. of  7 variables:
 $ region          : Factor w/ 3 levels "England","Scotland",..: 1 1 1 1 1 1 1 1 NA NA ...
 $ party           : Factor w/ 8 levels "Conservative",..: 1 2 3 4 5 6 7 8 1 2 ...
 $ flng.leaders    : num  3 6 3 NA 5 NA NA NA 7 3 ...
 $ flng.parties    : num  6 5 4 NA NA 7 3 0 6 1 ...
 $ id              : int  1 1 1 1 1 1 1 1 2 2 ...
 $ rel.flng.leaders: num  -1.25 1.75 -1.25 NA 0.75 NA NA NA 2.5 -1.5 ...
 $ rel.flng.parties: num  1.833 0.833 -0.167 NA NA ...
 - attr(*, "reshapeLong")=List of 4
  ..$ varying:List of 2
  .. ..$ flng.leaders: chr [1:8] "flng.cameron" "flng.brown" "flng.clegg" "flng.salmond" ...
  .. ..$ flng.parties: chr [1:8] "flng.cons" "flng.labour" "flng.libdem" "flng.snp" ...
  ..$ v.names: chr [1:2] "flng.leaders" "flng.parties"
  ..$ idvar  : chr "id"
  ..$ timevar: chr "party"

Groupwise computations using withinGroups() from the package memisc. You may need to install this package using install.packages("memisc") from CRAN if you want to run this on your computer. (The package is already installed on the notebook container, however.)

library(memisc)

Loading required package: lattice
Loading required package: MASS

Attaching package: 'memisc'

The following object is masked _by_ '.GlobalEnv':

    Mean

The following objects are masked from 'package:stats':

    contr.sum, contr.treatment, contrasts

The following object is masked from 'package:base':

    as.array

bes2010flngs_pre_long <- withinGroups(bes2010flngs_pre_long,
                                      ~id,{
     rel.flng.parties <- flng.parties - Mean(flng.parties)
     rel.flng.leaders <- flng.leaders - Mean(flng.leaders)
    })

We use ‘head’ to look at the first 14 elements of the re-combined data frame:

head(bes2010flngs_pre_long[-(1:2)],n=14)

               flng.leaders flng.parties id rel.flng.leaders rel.flng.parties
1.Conservative            3            6  1            -1.25        1.8333333
1.Labour                  6            5  1             1.75        0.8333333
1.LibDem                  3            4  1            -1.25       -0.1666667
1.SNP                    NA           NA  1               NA               NA
1.Plaid Cymru             5           NA  1             0.75               NA
1.Green                  NA            7  1               NA        2.8333333
1.UKIP                   NA            3  1               NA       -1.1666667
1.BNP                    NA            0  1               NA       -4.1666667
2.Conservative            7            6  2             2.50        2.6666667
2.Labour                  3            1  2            -1.50       -2.3333333
2.LibDem                  5            7  2             0.50        3.6666667
2.SNP                    NA           NA  2               NA               NA
2.Plaid Cymru             3           NA  2            -1.50               NA
2.Green                  NA            6  2               NA        2.6666667