Displaying 3 results from an estimated 3 matches for "xmiss".
Did you mean:
miss
2011 Mar 23
0
Rulefit with R and missing values
...ref<- array(1, dim=c(tt[1],tt[2]-1))
resp<- array(1, dim=c(tt[1],1))
for ( i in 1 : tt[1]) {
resp[i,1]=satisf1[i,tt[2]]
for (j in 1 : (tt[2]-1)) {
ref[i,j]=satisf1[i,j]
}
}
erreur_pred<-array(1, dim=c(tt[1],1))
rfmod = rulefit (ref,resp,rfmode="class")
Erreur dans if (xmiss <= bgstx) stop(paste("value of xmiss =", xmiss, "is
smaller than largest predictor variable value =", :
valeur manquante l? o? TRUE / FALSE est requis
--
View this message in context: http://r.789695.n4.nabble.com/Rulefit-with-R-and-missing-values-tp3399190p3399190.html...
2005 Jun 06
1
Missing values in argument of .Fortran.
...a different thing if it is missing.
The way I am thinking of proceeding is along the xlines of:
ymiss <- is.na(y)
rslt <- .Fortran(
"foo",
NAOK=TRUE,
as.double(y),
as.logical(ymiss),
etc,
etc
)
and inside ``foo'' have a logical branch based on the value of
xmiss(i).
Questions:
(1) Is there a sexier way to proceed? E.g. is it possible
within (g77) fortran to detect the fact that y(i) is/was an
NA (or not) and make the nature of y(i) the basis of an
if-statement?
(2) Are there any lurking pitfalls in the use of the NAOK=TRUE
argument?
(3) Is ther...
2011 Jun 03
3
Not missing at random
Hello!
I would like to sample 30 % of cases (with at least 1 value lower than 3) and
among them I want to set all values lower than 3 (within selected cases) as NA
(NMAR- Not missing at random). I managed to sample cases, but I don’t know how
to set values (lower than 3) as NA.
R code:
x <-