impKNNa {robCompositions} | R Documentation |
This function offers several knn methods for the imputation of missing values in compositional data.
impKNNa(x, method = "knn", k = 3, metric = "Aitchison", agg = "median", primitive = FALSE, normknn = TRUE, das = FALSE)
x |
data frame or matrix |
method |
method (at the moment, only “knn” can be used) |
k |
number of nearest neighbors chosen for imputation |
metric |
“Aichison” or “Euclidean” |
agg |
“median” or “mean”, for the aggregation of the nearest neighbors |
primitive |
if TRUE, a more enhanced search for the $k$-nearest neighbors is obtained (see details) |
normknn |
An adjustment of the imputed values is performed if TRUE |
das |
depricated. if TRUE, the original definition of the Aitchison distance is used to calculate distances between observations. if FALSE, a version using the clr transformation is used. |
The Aitchison metric
should be chosen when dealing with compositional data, the Euclidean metric
otherwise. \
If primitive
== FALSE, a sequential search for the k-nearest neighbors
is applied for every missing value where all information corresponding to the
non-missing cells plus the information in the variable to be imputed plus some
additional information is available. If primitive
== TRUE, a search of the
k-nearest neighbors among observations is applied where in addition to the variable
to be imputed any further cells are non-missing. \
If normknn
is TRUE (prefered option) the imputed cells from a nearest neighbor method are adjusted with special adjustment factors (more details can be found online (see the references)).
xOrig |
Original data frame or matrix |
xImp |
Imputed data |
w |
Amount of imputed values |
wind |
Index of the missing values in the data |
metric |
Metric used |
Matthias Templ
Hron, K. and Templ, M. and Filzmoser, P. (2008) Imputation of missing values for compositional data using classical and robust methods Research Report SM-2008-4, Vienna University of Technology, 15 pages.
data(aitchison395) x <- aitchison395 x[1,3] x[1,3] <- NA xi <- impKNNa(x)$xImp xi[1,3]