Arguments
aDataFrame
A data frame containing columns with missing SD's (coded as
NA) and their complete means (used only for nearest-neighbor method).
columnSDnames
Label of the column(s) with missing SD. Can be a string
or list of strings.
columnXnames
Label of the column(s) with means (X) for each SD. Can be
a string or list of strings. Must be complete with no missing data.
method
The method used to impute the missing SD's. The default is
"Bracken1992" which applies Bracken's (1992) approach to impute SD using
the coefficient of variation from all complete cases. Other options include:
"HotDeck"
range
A positive number on the range of neighbours to sample from for
imputing SD's. Used in combination with "HotDeck_NN". The default
is 3; which indicates that the 3 means that are most similar in rank order
to the mean with the missin
M
The number of imputed datasets to return. Currently only works
for "HotDeck" method.