Package 'Hmisc' - R

16 aregImpute
that only monotonic transformations of left and right-side variables are allowed, every bootstrap
resample will give predicted values of the target variable that are monotonically related to predicted
values from every other bootstrap resample. The same is true for Bayesian predicted values. This
causes predictive mean matching to always match on the same donor observation.
When the missingness mechanism for a variable is so systematic that the distribution of observed
values is truncated, predictive mean matching does not work. It will only yield imputed values that
are near observed values, so intervals in which no values are observed will not be populated by imputed
values. For this case, the only hope is to make regression assumptions and use extrapolation.
With type="regression", aregImpute will use linear extrapolation to obtain a (hopefully)
reasonable distribution of imputed values. The "regression" option causes aregImpute to
impute missing values by adding a random sample of residuals (with replacement if there are more
NAs than measured values) on the transformed scale of the target variable. After random residuals
are added, predicted random draws are obtained on the original untransformed scale using reverse
linear interpolation on the table of original and transformed target values (linear extrapolation when
a random residual is large enough to put the random draw prediction outside the range of observed
values). The bootstrap is used as with type="pmm" to factor in the uncertainty of the imputation
model.
As model uncertainty is high when the transformation of a target variable is unknown, tlinear
defaults to TRUE to limit the variance in predicted values when nk is positive.
Value
a list of class "aregImpute" containing the following elements:
call
formula
match
fweighted
n
p
na
nna
type
tlinear
nk
cat.levels
df
n.impute
imputed
x
rsq
the function call expression
the formula specified to aregImpute
the match argument
the fweighted argument
total number of observations in input dataset
number of variables
list of subscripts of observations for which values were originally missing
named vector containing the numbers of missing values in the data
vector of types of transformations used for each variable ("s","l","c" for
smooth spline, linear, or categorical with dummy variables)
value of tlinear parameter
number of knots used for smooth transformations
list containing character vectors specifying the levels of categorical variables
degrees of freedom (number of parameters estimated) for each variable
number of multiple imputations per missing value
a list containing matrices of imputed values in the same format as those created
by transcan. Categorical variables are coded using their integer codes.
Variables having no missing values will have NULL matrices in the list.
if x is TRUE, the original data matrix with integer codes for categorical variables
for the last round of imputations, a vector containing the R-squares with which
each sometimes-missing variable could be predicted from the others by ace or
avas.