mice Imputation Methods — syn_mice" />
syn_mice.Rd
Constructs synthetic dataset with mice imputation methods. The functionality
is very similar to the functionality of
synthpop::syn
in the synthpop package
(Nowok, Raab, & Dibben, 2016). Methods defined in synthpop are accessible
via mice.impute.synthpop
(see Examples).
syn_mice(data, m=5, k=NULL, syn_check=TRUE, ...)
data | Original data frame |
---|---|
m | Number of synthetic datasets |
k | Number of observations in synthetic data |
syn_check | Logical indicating whether checks in
|
... | Further arguments to be passed, with conventions in
|
Object of class synds
, see synthpop::syn
.
Nowok, B., Raab, G., & Dibben, C. (2016). synthpop: Bespoke creation of synthetic data in R. Journal of Statistical Software, 74(11), 1-26. doi: 10.18637/jss.v074.i11
if (FALSE) { ############################################################################# # EXAMPLE 1: Synthesization of SD2011 using mice functionality ############################################################################# library(synthpop) #** selection of dataset data(SD2011, package="synthpop") vars <- c("sex","age","ls","smoke") dat <- SD2011[1:1000, vars] dat$ls <- as.numeric(dat$ls) #** default synthesis imp0 <- synthpop::syn(dat) pred0 <- imp0$predictor.matrix method0 <- imp0$method #* define imputation methods method <- c(sex="synthpop", age="synthpop", ls="synthpop", smoke="logreg") # only for smoke, an original mice imputation method is used #- define synthpop functions synthpop_fun <- list(sex="constant", age="constant", ls="cart") #- arguments for 'syn.cart' method synthpop_args <- list(ls=list(smoothing="density")) #- fixed values for 'syn.constant' method fixed_values <- dat[,1:2] #- do synthesization imp <- miceadds::syn_mice(dat, m=1, synthpop_fun=synthpop_fun, method=method, pedictorMatrix=pred0, rf.fixed_values=fixed_values, synthpop_args=synthpop_args) summary(imp) }